DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement submitted on 02/17/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Amendment
The Amendment filed on 02/17/2026 has been entered. Claims 31-34 are added. Claims 1-34 remain pending in the application.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-34 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Claims 1-27 are directed to a method and claims 29-34 are directed to a device. Therefore, the claims are eligible under Step 1 for being directed to a process and a machine respectively.
Independent claims 1 and 29:
Step 2A Prong 1:
Claims recite:
determining, using a first autoencoder, a feature vector associated with one or more features associated with an environment of the client - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and selecting data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper;
determining a latent vector using a second autoencoder and based at least in part on the feature vector - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and selecting data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
A method of wireless communication performed by client; An apparatus for wireless communication at a client, comprising: one or more memories; and one or more processors, coupled to the one or more memories - These limitations amount to components of a general purpose computer that applies a judicial exception, by use of conventional computer functions (see MPEP § 2106.05(b)).
the latent vector comprises compressed channel state feedback - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
transmitting the feature vector and the latent vector - the steps recited at a high level of generality, and amounts to mere data transmitting which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
A method of wireless communication performed by client; An apparatus for wireless communication at a client, comprising: one or more memories; and one or more processors, coupled to the one or more memories - These limitations amount to components of a general purpose computer that applies a judicial exception, by use of conventional computer functions (see MPEP § 2106.05(b)).
the latent vector comprises compressed channel state feedback - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
transmitting the feature vector and the latent vector - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 2:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
a first encoder configured to receive an observed environmental vector as input and to provide the feature vector as output; and a first decoder configured to receive the feature vector as input and to provide the observed environmental vector as output - These additional elements are recited at a high level of generality and merely invokes a generic computer machinery as a tool to perform the underlying abstract ideas and thus fails to integrate the abstract idea into a practical application. See MPEP 2106.05(f).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The additional elements from Step 2A Prong 2 include invoking computers or other machinery to apply the underlying judicial exception and generally linking the use of the judicial exception to indicate a field of use or technological environment. Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP 2106.05.
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 3:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
a second encoder configured to receive an observed wireless communication vector and the feature vector as input and to provide the latent vector as output; and a second decoder configured to receive the latent vector and the feature vector as input and to provide the observed wireless communication vector as output - These additional elements are recited at a high level of generality and merely invokes a generic computer machinery as a tool to perform the underlying abstract ideas and thus fails to integrate the abstract idea into a practical application. See MPEP 2106.05(f).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The additional elements from Step 2A Prong 2 include invoking computers or other machinery to apply the underlying judicial exception and generally linking the use of the judicial exception to indicate a field of use or technological environment. Thus, the additional elements, viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP 2106.05.
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 4:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein determining the feature vector comprises providing an observed environmental vector as input to the first autoencoder - the steps recited at a high level of generality, and amounts to mere data gathering which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g));
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein determining the feature vector comprises providing an observed environmental vector as input to the first autoencoder - the steps recited at a high level of generality, and amounts to mere data gathering which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g));
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 5:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the observed environmental vector comprises one or more feature components, wherein the one or more feature components indicate:
a client vendor identifier,
a client antenna configuration,
a large scale channel characteristic,
a channel state information reference signal configuration,
an image obtained by an imaging device,
a portion of an estimated propagation channel, or
a combination thereof - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the observed environmental vector comprises one or more feature components, wherein the one or more feature components indicate:
a client vendor identifier,
a client antenna configuration,
a large scale channel characteristic,
a channel state information reference signal configuration,
an image obtained by an imaging device,
a portion of an estimated propagation channel, or
a combination thereof - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 6:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the large scale channel characteristic indicates:
a delay spread associated with a channel,
a power delay profile associated with a channel,
a Doppler measurement associated with a channel,
a Doppler spectrum associated with a channel,
a signal to noise ratio associated with a channel
a signal to noise plus interference ratio associated with a channel,
a reference signal received power,
a received signal strength indicator, or
a combination thereof - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the large scale channel characteristic indicates:
a delay spread associated with a channel,
a power delay profile associated with a channel,
a Doppler measurement associated with a channel,
a Doppler spectrum associated with a channel,
a signal to noise ratio associated with a channel
a signal to noise plus interference ratio associated with a channel,
a reference signal received power,
a received signal strength indicator, or
a combination thereof - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 7:
Step 2A Prong 1:
Claim recites:
wherein the latent vector is associated with a wireless communication task, wherein the wireless communication task comprises:
determining channel state feedback (CSF),
determining positioning information associated with the client,
determining a modulation associated with a wireless communication,
determining a waveform associated with a wireless communication, or
a combination thereof - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and selecting data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2 & Step 2B: There are no additional elements recited so the claims do not provide a practical application and is not considered to be significantly more. As such, the claims are ineligible.
Dependent claim 8:
Step 2A Prong 1:
Claim recites:
determining CSI based at least in part on the CSI-RS - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and selecting data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
receiving a channel state information (CSI) reference signal (CSI-RS) - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
providing the CSI as input to the second autoencoder - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
receiving a channel state information (CSI) reference signal (CSI-RS) - - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
providing the CSI as input to the second autoencoder - - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 9:
Step 2A Prong 1: The claim recites the abstract ideas of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
transmitting the feature vector and the latent vector using: a physical uplink control channel, a physical uplink shared channel, or a combination thereof - the steps recited at a high level of generality, and amounts to mere data transmission which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
transmitting the feature vector and the latent vector using: a physical uplink control channel, a physical uplink shared channel, or a combination thereof - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 10:
Step 2A Prong 1: The claim recites the abstract ideas of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein at least one of the first autoencoder or the second autoencoder comprises a variational autoencoder - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein at least one of the first autoencoder or the second autoencoder comprises a variational autoencoder - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 11:
Step 2A Prong 1: The claim recites the abstract ideas of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
training at least one of the first autoencoder or the second autoencoder - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
training at least one of the first autoencoder or the second autoencoder - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 12:
Step 2A Prong 1: The claim recites the abstract ideas of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises using a reparameterization - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises using a reparameterization - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 13:
Step 2A Prong 1:
Claim recites:
determining a set of neural network parameters that maximize a variational lower bound function corresponding to the first autoencoder and the second autoencoder - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and selecting data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2 & Step 2B: There are no additional elements recited so the claims do not provide a practical application and is not considered to be significantly more. As such, the claims are ineligible.
Dependent claim 14:
Step 2A Prong 1:
Claim recites:
wherein a negative variational lower bound function corresponds to a sum of a first loss function associated with the first autoencoder and a second loss function associated with the second autoencoder - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses a mathematical concept of a mathematical calculation of calculating using mathematical methods to determine a negative variational lower bound function.
Step 2A Prong 2 & Step 2B: There are no additional elements recited so the claims do not provide a practical application and is not considered to be significantly more. As such, the claims are ineligible.
Dependent claim 15:
Step 2A Prong 1:
Claim recites:
wherein the first loss function comprises a first reconstruction loss and a first regularization term for the first autoencoder, and wherein the second loss function comprises a second reconstruction loss and a second regularization term for the second autoencoder - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses a mathematical concept of a mathematical relationship.
Step 2A Prong 2 & Step 2B: There are no additional elements recited so the claims do not provide a practical application and is not considered to be significantly more. As such, the claims are ineligible.
Dependent claim 16:
Step 2A Prong 1:
Claim recites:
wherein the variational lower bound function does not include a regularization term - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses a mathematical concept of a mathematical relationship.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the first autoencoder and the second autoencoder are regular autoencoders - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the first autoencoder and the second autoencoder are regular autoencoders - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 17:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises training the first autoencoder and the second autoencoder to determine a format of the feature vector - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises training the first autoencoder and the second autoencoder to determine a format of the feature vector - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 18:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises using an unsupervised learning procedure - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises using an unsupervised learning procedure - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 19:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a fully federated learning procedure, and wherein performing the fully federated learning procedure comprises jointly training the first autoencoder and the second autoencoder - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a fully federated learning procedure, and wherein performing the fully federated learning procedure comprises jointly training the first autoencoder and the second autoencoder - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 20:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a fully federated learning procedure, and wherein performing the fully federated learning procedure comprises alternating between training the first autoencoder and training the second autoencoder - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a fully federated learning procedure, and wherein performing the fully federated learning procedure comprises alternating between training the first autoencoder and training the second autoencoder - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 21:
Step 2A Prong 1: The claim recites the abstract ideas of claims 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
performing a first plurality of training iterations associated with the first autoencoder according to a first training frequency; and
performing a second plurality of training iterations associated with the second autoencoder according to a second training frequency that is higher than the first training frequency - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
performing a first plurality of training iterations associated with the first autoencoder according to a first training frequency; and
performing a second plurality of training iterations associated with the second autoencoder according to a second training frequency that is higher than the first training frequency - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 22:
Step 2A Prong 1: The claim recites the abstract ideas of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises: providing an observed environmental vector to a server; and receiving the first autoencoder from the server, wherein the first autoencoder is based at least in part on the observed environmental vector - the steps recited at a high level of generality, and amounts to mere data transmitting/receiving which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises: providing an observed environmental vector to a server; and receiving the first autoencoder from the server, wherein the first autoencoder is based at least in part on the observed environmental vector - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 23:
Step 2A Prong 1: The claim recites the abstract ideas of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the first autoencoder is based at least in part on at least one additional environmental vector associated with at least one additional client - the step recited at a high level of generality, and amounts to selecting a particular data source or type of data to be manipulated, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the first autoencoder is based at least in part on at least one additional environmental vector associated with at least one additional client - viewed individually or in combination, describes selecting a particular data source or type of data to be manipulated similar to selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display described in MPEP § 2106.05(g).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 24:
Step 2A Prong 1: The claim recites the abstract ideas of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises:
updating the second autoencoder to determine a set of updated neural network parameters - the steps recited at a high level of generality, and amounts to mere data modifying which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)); and
transmitting the set of updated neural network parameters to a server - the steps recited at a high level of generality, and amounts to mere data transmission which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises:
updating the second autoencoder to determine a set of updated neural network parameters - the steps recited at a high level of generality, and amounts to mere data modifying which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)); and
transmitting the set of updated neural network parameters to a server - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 25:
Step 2A Prong 1: The claim recites the abstract ideas of claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
performing a first plurality of training iterations associated with the first autoencoder according to a first training frequency - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
wherein performing a training iteration of the first plurality of training iterations comprises:
providing an observed environmental vector to a server; and receiving an updated first autoencoder from the server, wherein the updated first autoencoder is based at least in part on the observed environmental vector - the steps recited at a high level of generality, and amounts to mere data transmitting/receiving which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
; and
performing a second plurality of training iterations associated with the second autoencoder according to a second training frequency that is higher than the first training frequency - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
performing a first plurality of training iterations associated with the first autoencoder according to a first training frequency - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
wherein performing a training iteration of the first plurality of training iterations comprises:
providing an observed environmental vector to a server; and receiving an updated first autoencoder from the server, wherein the updated first autoencoder is based at least in part on the observed environmental vector - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
; and
performing a second plurality of training iterations associated with the second autoencoder according to a second training frequency that is higher than the first training frequency - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 26:
Step 2A Prong 1:
Claim recites:
obtaining an observed environmental training vector - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of obtaining and evaluating data, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper;
obtaining an observed wireless communication training vector - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of obtaining and evaluating data, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper;
determining a loss associated with the second autoencoder based at least in part on the second training output, wherein the loss is associated with the set of neural network parameters;
determining a plurality of gradients of the loss with respect to a set of autoencoder parameters, wherein the set of autoencoder parameters corresponds to the second autoencoder - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and selecting data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
performing a partial federated learning procedure - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
receiving, from a server, a set of neural network parameters associated with the first autoencoder and the second autoencoder - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
inputting the observed environmental training vector to a first encoder of the first autoencoder to determine a training feature vector - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
inputting the training feature vector and the observed wireless communication training vector to a second encoder of the second autoencoder to determine a training latent vector - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
inputting the training feature vector and the training latent vector to a second decoder of the second autoencoder to determine a second training output of the second autoencoder - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
updating the set of autoencoder parameters based at least in part on the plurality of gradients - the steps recited at a high level of generality, and amounts to mere data modifying which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
updating the set of autoencoder parameters a specified number of times to determine a final set of updated autoencoder parameters - the steps recited at a high level of generality, and amounts to mere data modifying which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
; and
transmitting the final set of updated autoencoder parameters to the server - the steps recited at a high level of generality, and amounts to mere data transmission which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
performing a partial federated learning procedure - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
receiving, from a server, a set of neural network parameters associated with the first autoencoder and the second autoencoder - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
inputting the observed environmental training vector to a first encoder of the first autoencoder to determine a training feature vector - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
inputting the training feature vector and the observed wireless communication training vector to a second encoder of the second autoencoder to determine a training latent vector - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
inputting the training feature vector and the training latent vector to a second decoder of the second autoencoder to determine a second training output of the second autoencoder - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
updating the set of autoencoder parameters based at least in part on the plurality of gradients - the steps recited at a high level of generality, and amounts to mere data modifying which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
updating the set of autoencoder parameters a specified number of times to determine a final set of updated autoencoder parameters - the steps recited at a high level of generality, and amounts to mere data modifying which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
; and
transmitting the final set of updated autoencoder parameters to the server - the steps recited at a high level of generality, and amounts to mere data transmission which is well known which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Independent claims 27 and 30:
Step 2A Prong 1:
Claims recite:
determining an observed wireless communication vector based at least in part on the feature vector and the latent vector - Under its broadest reasonable interpretation in light of the specification, this limitation encompasses the mental process of evaluating data and selecting data based on judgement, which is observing, evaluating and judging that is practically capable of being performed in the human mind with the assistance of pen and paper.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
A method of wireless communication performed by a server; An apparatus for wireless communication at a server, comprising: one or more memories; and one or more processors, coupled to the one or more memories - These limitations amount to components of a general purpose computer that applies a judicial exception, by use of conventional computer functions (see MPEP § 2106.05(b)).
receiving, from a client, a feature vector associated with one or more features associated with an environment of the client - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
receiving, from the client, a latent vector that is based at least in part on the feature vector - the step recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
the latent vector comprises compressed channel state feedback - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
performing a wireless communication action based at least in part on determining the observed wireless communication vector - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
A method of wireless communication performed by a server; An apparatus for wireless communication at a server, comprising: one or more memories; and one or more processors, coupled to the one or more memories - These limitations amount to components of a general purpose computer that applies a judicial exception, by use of conventional computer functions (see MPEP § 2106.05(b)).
receiving, from a client, a feature vector associated with one or more features associated with an environment of the client - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
receiving, from the client, a latent vector that is based at least in part on the feature vector - which is a well-understood, routine, conventional activity similar to receiving or transmitting data over a network described in MPEP 2106.05(d)(II).
the latent vector comprises compressed channel state feedback - the step recited at a high level of generality, and amounts to mere data description, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
performing a wireless communication action based at least in part on determining the observed wireless communication vector - the step recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 28:
Step 2A Prong 1: The claim recites the abstract ideas of claim 27.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the feature vector is based at least in part on an observed environmental vector - the step recited at a high level of generality, and amounts to selecting a particular data source or type of data to be manipulated, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the feature vector is based at least in part on an observed environmental vector - viewed individually or in combination, describes selecting a particular data source or type of data to be manipulated similar to selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display described in MPEP § 2106.05(g).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 31:
Step 2A Prong 1: The claim recites the abstract ideas of claim 29.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the first autoencoder and the second autoencoder are trained using a federated learning procedure - the step recited at a high level of generality, and amounts to merely indicating a field of use or technological environment in which the judicial exception is performed (see MPEP § 2106.05(h)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the first autoencoder and the second autoencoder are trained using a federated learning procedure - generally linking the use of the judicial exception to indicate a field of use or technological environment. Viewed individually or in combination, do not provide an inventive concept or otherwise amount to significantly more than the abstract idea itself. See MPEP 2106.05.
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 32:
Step 2A Prong 1: The claim recites the abstract ideas of claim 29.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the feature vector comprises information indicative of a client antenna configuration or a large scale channel characteristic - the step recited at a high level of generality, and amounts to selecting a particular data source or type of data to be manipulated, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the feature vector comprises information indicative of a client antenna configuration or a large scale channel characteristic - viewed individually or in combination, describes selecting a particular data source or type of data to be manipulated similar to selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display described in MPEP § 2106.05(g).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 33:
Step 2A Prong 1: The claim recites the abstract ideas of claim 30.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the server is further configured to update a model parameter based on the feature vector and latent vector - the steps recited at a high level of generality, and amounts to mere data modifying which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the server is further configured to update a model parameter based on the feature vector and latent vector - the steps recited at a high level of generality, and amounts to mere data modifying which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Dependent claim 34:
Step 2A Prong 1: The claim recites the abstract ideas of claim 30.
Step 2A Prong 2: This judicial exception is not integrated into a practical application because they recite the additional elements:
wherein the wireless communication action comprises selection of a modulation scheme or waveform for subsequent communication with the client - the step recited at a high level of generality, and amounts to selecting a particular data source or type of data to be manipulated, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are thus directed to the abstract idea.
Step 2B: The claims do not include additional elements that amount to significantly more than the judicial exception.
The additional elements:
wherein the wireless communication action comprises selection of a modulation scheme or waveform for subsequent communication with the client - viewed individually or in combination, describes selecting a particular data source or type of data to be manipulated similar to selecting information, based on types of information and availability of information in a power-grid environment, for collection, analysis and display described in MPEP § 2106.05(g).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. As such, the claims are ineligible.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-8, 10-14 and 17-33 are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG et al. (hereinafter ZHANG), US 20210406765 A1, in view of Ye et al. (hereinafter Ye), "Channel Agnostic End-to-End Learning Based Communication Systems with Conditional GAN," 2018 IEEE Globecom Workshops (GC Wkshps), Abu Dhabi, United Arab Emirates, 2018, pp. 1-5, doi: 10.1109/GLOCOMW.2018.8644250.
Regarding independent claim 1, ZHANG teaches a method
determining, using a first autoencoder, a feature vector associated with one or more features associated with an environment of the client ([0048] FIG. 2 illustrates an example computing apparatus 200 for implementing an artificial intelligence (AI) algorithm including a machine-learning (ML) model in accordance with embodiments described herein. The computing apparatus 200 may comprise one or more user terminals, such as a desktop computer, laptop computer, tablet, smartphone, wearable smart device such as a smart watch, or an on-board computer of a vehicle such as car, etc. Additionally or alternatively, the computing apparatus 200 may comprise a server. A server herein refers to a logical entity which may comprise one or more physical server units located at one or more geographic sites. Where required, distributed or “cloud” computing techniques are in themselves known in the art. The one or more user terminals and/or the one or more server units of the server may be connected to one another via a packet-switched network, which may comprise for example a wide-area internetwork such as the Internet, a mobile cellular network such as a 3GPP network, a wired local area network (LAN) such as an Ethernet network, or a wireless LAN such as a Wi-Fi, Thread or 6LoWPAN network; [0060] For instance, consider a simple example as in FIG. 1C where the machine-learning model comprises a single neural network 101, arranged to take a feature vector X as its input 108i and to output a classification Y as its output 108o. The input feature vector X comprises a plurality of elements x.sub.d, each representing a different feature d=0, 1, 2, . . . etc. E.g. in the example of image recognition, each element of the feature vector X may represent a respective pixel value. For instance one element represents the red channel for pixel (0,0); another element represents the green channel for pixel (0,0); another element represents the blue channel of pixel (0,0); another element represents the red channel of pixel (0,1); and so forth. As another example, where the neural network is used to make a medical diagnosis, each of the elements of the feature vector may represent a value of a different symptom of the subject, physical feature of the subject, or other fact about the subject (e.g. body temperature, blood pressure, etc.); [0061] FIG. 3 shows an example data set comprising a plurality of data points i=0, 1, 2, . . . etc. Each data point i comprises a respective set of values of the feature vector (where x.sub.id is the value of the d.sub.th feature in the i.sub.th data point). The input feature vector X.sub.i represents the input observations for a given data point, where in general any given observation i may or may not comprise a complete set of values for all the elements of the feature vector X; [0048] FIG. 2 illustrates an example computing apparatus 200 for implementing an artificial intelligence (AI) algorithm including a machine-learning (ML) model in accordance with embodiments described herein. The computing apparatus 200 may comprise one or more user terminals, such as a desktop computer, laptop computer, tablet, smartphone, wearable smart device such as a smart watch, or an on-board computer of a vehicle such as car, etc. Additionally or alternatively, the computing apparatus 200 may comprise a server. A server herein refers to a logical entity which may comprise one or more physical server units located at one or more geographic sites. Where required, distributed or “cloud” computing techniques are in themselves known in the art. The one or more user terminals and/or the one or more server units of the server may be connected to one another via a packet-switched network, which may comprise for example a wide-area internetwork such as the Internet, a mobile cellular network such as a 3GPP network, a wired local area network (LAN) such as an Ethernet network, or a wireless LAN such as a Wi-Fi, Thread or 6LoWPAN network);
determining a latent vector using a second autoencoder and based at least in part on the feature vector ([0068] The encoder 208q is arranged to receive the observed feature vector X.sub.o as an input and encode it into a latent vector Z (a representation in a latent space; [0074] FIG. 4B shows a more abstracted representation of a VAE such as shown in FIG. 4A; [0075] FIG. 4C shows an even higher level representation of a VAE such as that shown in FIGS. 4A and 4B. In FIG. 4C the solid lines represent a generative network of the decoder 208q, and the dashed lines represents an inference network of the encoder 208p. In this form of diagram, a vector shown in a circle represents a vector of distributions. So here, each element of the feature vector X (=x.sub.1 . . . x.sub.d) is modelled as a distribution, e.g. as discussed in relation to FIG. 1C. Similarly each element of the latent vector Z is modelled as a distribution. On the other hand, a vector shown without a circle represents a fixed point. So in the illustrated example, the weights θ of the generative network are modelled as simple values, not distributions (though that is a possibility as well). The rounded rectangle labelled N represents the “plate”, meaning the vectors within the plate are iterated over a number N of learning steps (one for each data point). In other words i=0, . . . , N−1. A vector outside the plate is global, i.e. it does not scale with the number of data points i (nor the number of features d in the feature vector). The rounded rectangle labelled D represents that the feature vector X comprises multiple elements x.sub.1 . . . x.sub.d)); and
transmitting the feature vector and the latent vector ([0068] The encoder 208q is arranged to receive the observed feature vector X.sub.o as an input and encode it into a late9nt vector Z (a representation in a latent space). The decoder 208p is arranged to receive the latent vector Z and decode back to the original feature space of the feature vector. The version of the feature vector output by the decoder 208p may be labelled herein X).
ZHANG does not explicitly teach a method of wireless communication performed by client, a latent vector comprising compressed channel state feedback.
However, in the same field of endeavor, Ye teaches a method of wireless communication performed by client (Fig. 2, Transmitter; Abstract, “In this article, we use deep neural networks (DNNs) to develop an end-to-end wireless communication system, in which DNNs are employed for all signal-related functionalities, including encoding, decoding, modulation, and equalization. However, accurate instantaneous channel transfer function, i.e., the channel state information (CSI), is necessary to compute the gradient of the DNN representing. In many communication systems, the channel transfer function is hard to obtain in advance and varies with time and location. In this article, this constraint is released by developing a channel agnostic end-to-end system that does not rely on any prior information about the channel. We use a conditional generative adversarial net (GAN) to represent the channel effects, where the encoded signal of the transmitter (i.e. client) will serve as the conditioning information. In addition, in order to obtain accurate channel state information for signal detection at the receiver, the received signal corresponding to the pilot data is added as a part of the conditioning information”), a latent vector comprising compressed channel state feedback (page 3, left column, 1st paragraph “… If the discriminator, D, can successfully classify the samples of the two sources, then its success will be used to generate a feed back to the generator, G, so that the generator, G, can learn to produce samples more similar to the real samples …”).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of the end-to-end communication system learning the implements of the transmitter and the receiver using DNNs as suggested in Ye into ZHANG’s system because both of these systems are addressing both the transmitter and the receiver are represented by deep neural networks (DNNs) and can be interpreted as an auto-encoder and an auto-decoder, respectively. This modification would have been motivated by the desire to develop a channel agnostic end to-end learning based communication system, where different types of channel effects can be automatically learned without knowing the specific channel transfer function (Ye, page 2, left column, 1st paragraph).
Regarding dependent claim 2, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. ZHANG teaches wherein the first autoencoder comprises:
a first encoder configured to receive an observed environmental vector as input and to provide the feature vector as output ([0007] During a training phase, experience data comprising a large number of input data points X is supplied to the neural network, each data point comprising an example set of values for the feature vector; [0061] FIG. 3 shows an example data set comprising a plurality of data points i=0, 1, 2, . . . etc. Each data point i comprises a respective set of values of the feature vector (where xid is the value of the dth feature in the ith data point). The input feature vector Xi represents the input observations for a given data point; [0015] each stage in the sequence comprises: a variational auto-encoder, VAE, comprising a respective first encoder arranged to encode a respective subset of the real-world features into a respective latent space representation); and
a first decoder configured to receive the feature vector as input and to provide the observed environmental vector as output ([0015] a respective first decoder arranged to decode from the respective latent space representation to a respective decoded version of the respective set of real-world features).
Regarding dependent claim 3, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 2 that is incorporated. ZHANG teaches wherein the second autoencoder comprises:
a second encoder configured to receive an observed wireless communication vector and the feature vector as input and to provide the latent vector as output ([0068] The encoder 208q is arranged to receive the observed feature vector X.sub.o as an input and encode it into a latent vector Z (a representation in a latent space; [0074] FIG. 4B shows a more abstracted representation of a VAE such as shown in FIG. 4A; [0075] FIG. 4C shows an even higher level representation of a VAE such as that shown in FIGS. 4A and 4B. In FIG. 4C the solid lines represent a generative network of the decoder 208q, and the dashed lines represents an inference network of the encoder 208p. In this form of diagram, a vector shown in a circle represents a vector of distributions. So here, each element of the feature vector X (=x.sub.1 . . . x.sub.d) is modelled as a distribution, e.g. as discussed in relation to FIG. 1C. Similarly each element of the latent vector Z is modelled as a distribution. On the other hand, a vector shown without a circle represents a fixed point. So in the illustrated example, the weights θ of the generative network are modelled as simple values, not distributions (though that is a possibility as well). The rounded rectangle labelled N represents the “plate”, meaning the vectors within the plate are iterated over a number N of learning steps (one for each data point). In other words i=0, . . . , N−1. A vector outside the plate is global, i.e. it does not scale with the number of data points i (nor the number of features d in the feature vector). The rounded rectangle labelled D represents that the feature vector X comprises multiple elements x.sub.1 . . . x.sub.d)); and
a second decoder configured to receive the latent vector and the feature vector as input and to provide the observed wireless communication vector as output ([0069] The latent vector Z is a compressed (i.e. encoded) representation of the information contained in the input observations X.sub.o. No one element of the latent vector Z necessarily represents directly any real world quantity, but the vector Z as a whole represents the information in the input data in compressed form. It could be considered conceptually to represent abstract features abstracted from the input data X.sub.o, such as “wrinklyness” and “trunk-like-ness” in the example of elephant recognition (though no one element of the latent vector Z can necessarily be mapped onto any one such factor, and rather the latent vector Z as a whole encodes such abstract information). The decoder 208p is arranged to decode the latent vector Z back into values in a real-world feature space, i.e. back to an uncompressed form {circumflex over (X)} representing the actual observed properties (e.g. pixel values). The decoded feature vector {circumflex over (X)} has the same number of elements representing the same respective features as the input vector X.sub.o.).
Regarding dependent claim 4, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. ZHANG teaches wherein determining the feature vector comprises providing an observed environmental vector as input to the first autoencoder ([0061] FIG. 3 shows an example data set comprising a plurality of data points i=0, 1, 2, . . . etc. Each data point i comprises a respective set of values of the feature vector (where x.sub.id is the value of the d.sub.th feature in the i.sub.th data point). The input feature vector X.sub.i represents the input observations for a given data point, where in general any given observation i may or may not comprise a complete set of values for all the elements of the feature vector X).
Regarding dependent claim 5, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 4 that is incorporated. ZHANG teaches wherein the observed environmental vector comprises one or more feature components, wherein the one or more feature components indicate:
a client vendor identifier,
a client antenna configuration,
a large scale channel characteristic,
a channel state information reference signal configuration,
an image obtained by an imaging device,
a portion of an estimated propagation channel, or
a combination thereof ([0006] The input to the network is typically a vector, each element of the vector representing a different corresponding feature. E.g. in the case of image recognition the elements of this feature vector may represent different pixel values).
Regarding dependent claim 6, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 5 that is incorporated. Ye teaches wherein the large scale channel characteristic indicates:
a delay spread associated with a channel,
a power delay profile associated with a channel,
a Doppler measurement associated with a channel,
a Doppler spectrum associated with a channel,
a signal to noise ratio associated with a channel
a signal to noise plus interference ratio associated with a channel,
a reference signal received power,
a received signal strength indicator, or
a combination thereof (Ye, page 2, left column, 1st paragraph “in real communication systems, an accurate instantaneous CSI is hard to obtain in advance because the end-to-end channel often includes several types of random effects, such as channel noise and varying, which may be unknown or can not be expressed analytically”; Page 2, Section A. Conditional GAN “During the training, the generator maps an input noise, z, with prior distribution, pz(z), to a sample …”).
Regarding dependent claim 7, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. Ye teaches wherein the latent vector is associated with a wireless communication task, wherein the wireless communication task comprises:
determining channel state feedback (CSF),
determining positioning information associated with the client,
determining a modulation associated with a wireless communication,
determining a waveform associated with a wireless communication, or
a combination thereof (Ye, page 3, left column, 1st paragraph “If the discriminator, D, can successfully classify the samples of the two sources, then its success will be used to generate a feed back to the generator, G, so that the generator, G, can learn to produce samples more similar to the real samples”).
Regarding dependent claim 8, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 7 that is incorporated. Ye teaches wherein the wireless communication task comprises determining the CSF (page 3, left column, 1st paragraph “… If the discriminator, D, can successfully classify the samples of the two sources, then its success will be used to generate a feed back to the generator, G, so that the generator, G, can learn to produce samples more similar to the real samples …”), and wherein the method further comprises:
receiving a channel state information (CSI) reference signal (CSI-RS) (page 3, right column, 2nd paragraph “The instantaneous CSI, h, can be regarded as a sample from a large channel set H and is also vital coherent detection of the data at the receiver”);
determining CSI based at least in part on the CSI-RS (page 3, right column, 2nd paragraph “In order to obtain the CSI, a common practice is to send some pilot information to the receiver so that the channel information is inferred based on the received pilot information, yp.”); and
providing the CSI as input to the second autoencoder (page 3, right column, 2nd paragraph “the received pilot information, yp, is added as a part of the conditioning information so that the output samples follow the distribution of y given the input x and the received pilot data, yp”).
Regarding dependent claim 10, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. ZHANG further teaches wherein at least one of the first autoencoder or the second autoencoder comprises a variational autoencoder ([0067] FIG. 4A schematically illustrates one such example, known as a variational auto encoder (VAE). In this case the machine learning model 208 comprises an encoder 208q comprising an inference network, and a decoder 208p comprising a generative network. Each of the inference networks and the generative networks comprises one or more constituent neural networks 101, such as discussed in relation to FIG. 1A. An inference network for the present purposes means a neural network arranged to encode an input into a latent representation of that input, and a generative network means a neural network arranged to at least partially decode from a latent representation).
Regarding dependent claim 11, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 1 that is incorporated. ZHANG further teaches further comprising training at least one of the first autoencoder or the second autoencoder ([0015] According to one aspect disclosed herein, there is provided a computer-implemented method of training a model comprising a sequence of stages from a first stage to a last stage in the sequence, the model being trained based on i) a set of real-world features of a feature space associated with a target that are available for observation, and ii) a set of actions that are available to apply to the target, wherein the set of actions comprises observing at least one of the set of real-world features, and/or performing at least one task in order to affect a status of the target, wherein the model is trained to achieve a desired outcome, and wherein: each stage in the sequence comprises: a variational auto-encoder, VAE, comprising a respective first encoder arranged to encode a respective subset of the real-world features into a respective latent space representation, and a respective first decoder arranged to decode from the respective latent space representation to a respective decoded version of the respective set of real-world features; at least each but the last stage in the sequence comprises: a respective second decoder arranged to decode from the respective latent space representation to predict one or more respective actions; and each successive stage in the sequence following the first stage, each succeeding a respective preceding stage in the sequence, further comprises: a sequential network arranged to transform from the latent representation from the preceding stage to the latent space representation of the successive stage).
Regarding dependent claim 12, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG further teaches wherein training the at least one of the first autoencoder or the second autoencoder comprises using a reparameterization ([0056] Each node 104 represents a function of the input value(s) received on its input edges(s) 106i, the outputs of the function being output on the output edge(s) 106o of the respective node 104, such that the value(s) output on the output edge(s) 106o of the node 104 depend on the respective input value(s) according to the respective function. The function of each node 104 is also parametrized by one or more respective parameters w, sometimes also referred to as weights (not necessarily weights in the sense of multiplicative weights, though that is certainly one possibility). Thus the relation between the values of the input(s) 106i and the output(s) 106o of each node 104 depends on the respective function of the node and its respective weight(s); [0057] Each weight could simply be a scalar value. Alternatively, as shown in FIG. 1B, at some or all of the nodes 104 in the network 101, the respective weight may be modelled as a probabilistic distribution such as a Gaussian. In such cases the neural network 101 is sometimes referred to as a Bayesian neural network. Optionally, the value input/output on each of some or all of the edges 106 may each also be modelled as a respective probabilistic distribution. For any given weight or edge, the distribution may be modelled in terms of a set of samples of the distribution, or a set of parameters parameterizing the respective distribution, e.g. a pair of parameters specifying its centre point and width (e.g. in terms of its mean μ and standard deviation σ or variance σ.sup.2). The value of the edge or weight may be a random sample from the distribution. The learning or the weights may comprise tuning one or more of the parameters of each distribution).
Regarding dependent claim 13, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG further teaches wherein training the at least one of the first autoencoder or the second autoencoder comprises determining a set of neural network parameters that maximize a variational lower bound function corresponding to the first autoencoder and the second autoencoder ([0071] With each data point in the training data (each data point in the experience data during learning), the learning function 209 tunes the weights ø and θ so that the VAE 208 learns to encode the feature vector X into the latent space Z and back again. For instance, this may be done by minimizing a measure of divergence between q.sub.ø(Z.sub.i|X.sub.i) and p.sub.θ(X.sub.i|Z.sub.i), where q.sub.ø(Z.sub.i|X.sub.i) is a function parameterised by ø representing a vector of the probabilistic distributions of the elements of Z.sub.i output by the encoder 208q given the input values of X.sub.i, whilst p.sub.θ(X.sub.i|Z.sub.i) is a function parameterized by θ representing a vector of the probabilistic distributions of the elements of X.sub.i output by the encoder 208q given Z.sub.i. The symbol “|” means “given”. The model is trained to reconstruct X.sub.i and therefore maintains a distribution over X.sub.i. At the “input side”, the value of Xo.sub.i is known, and at the “output side”, the likelihood of {circumflex over (X)}.sub.i under the output distribution of the model is evaluated. Typically p(z|x) is referred to as posterior, and q(z|x) as approximate posterior. p(z) and q(z) are referred to as priors; [0144] We proposed to pre-train both the generative and inference models offline before learning the RL policies. In this case, we assume the access to the unobserved features, so that we can construct a supervised learning task to learn to impute unobserved features. Concretely, the pre-training task update the parameters θ, ϕ by maximizing the following variational lower-bound).
Regarding dependent claim 14, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 13 that is incorporated. Ye further teaches wherein a negative variational lower bound function corresponds to a sum of a first loss function associated with the first autoencoder and a second loss function associated with the second autoencoder (page 1, right column, 1st paragraph “the features and the parameters of a deep learning model can be learned directly from the data without handcraft or ad-hoc designs by optimizing an end-to-end loss function”; page 2, left column, 2nd paragraph “The conditioning information is the encoded signals from the transmitter along with the received pilot information used for estimating the channel. By iteratively training the conditional GAN, the transmitter, and the receiver, the end-to-end loss can be optimized in a supervised way”; page 3, Section III. END-TO-END COMMUNICATION SYSTEM).
Regarding dependent claim 17, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG further teaches wherein training the at least one of the first autoencoder or the second autoencoder comprises training the first autoencoder and the second autoencoder to determine a format of the feature vector ([0061] FIG. 3 shows an example data set comprising a plurality of data points i=0, 1, 2, . . . etc. Each data point i comprises a respective set of values of the feature vector (where xid is the value of the dth feature in the ith data point). The input feature vector Xi represents the input observations for a given data point, where in general any given observation i may or may not comprise a complete set of values for all the elements of the feature vector X. The classification Yi represents a corresponding classification of the observation i. In the training data an observed value of classification Yi is specified with each data point along with the observed values of the feature vector elements (the input data points in the training data are said to be “labelled” with the classification Yi)).
Regarding dependent claim 18, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG further teaches wherein training the at least one of the first autoencoder or the second autoencoder comprises using an unsupervised learning procedure ([0065] Explicit training based on labelled training data is sometimes referred to as a supervised approach. Other approaches to machine learning are also possible. For instance another example is the reinforcement approach. In this case, the neural network 101 begins making predictions of the classification Yi for each data point i, at first with little or no accuracy. After making the prediction for each data point i (or at least some of them), the AI algorithm 206 receives feedback (e.g. from a human) as to whether the prediction was correct, and uses this to tune the weights so as to perform better next time. Another example is referred to as the unsupervised approach. In this case the AI algorithm receives no labelling or feedback and instead is left to infer its own structure in the experienced input data; [0136] We introduce a sequential representation learning approach to facilitate the task of policy training with active feature acquisition. Let x1:T=(x1, . . . , xT) and a1:T=(a1, . . . , aT) denote a sequence of observations and actions, respectively. Alternatively, we also denote these sequences as x≤T and a≤T. Overall, our task of interest is to train a sequential representation learning model to learn the distribution of the full sequential observations x1:T, i.e., for both the observed part x1:T p and the unobserved part x1:T u. Given only partial observations, we can perform inference only with the observed features x1:T p. Therefore, our proposed approach extends the conventional unsupervised representation learning task to a supervised learning task, which learns to impute the unobserved features by synthesizing the acquired information and learning the model dynamics).
Regarding dependent claim 19, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG further teaches wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a fully federated learning procedure, and wherein performing the fully federated learning procedure comprises jointly training the first autoencoder and the second autoencoder ([0089] Referring first to FIG. 5A, at each stage t (t=0 . . . T) of the sequential model 208′, a respective VAE is trained for each of a set of observed features, e.g. X10 and X20 at stage t=0. In FIG. 5A, for a feature Xit, i indicates the feature itself, whilst t indicates the stage at which the feature is observed or generated, as the case may be. Only three features are shown here by way of illustration, but it will be appreciated that other numbers could be used. The observed features together form a respective group of the feature space. That is, each group comprises a different respective one or more of the features of the feature space. I.e. each group is a different one or more of the elements of the observed feature vector Xot. In the example of FIG. 5A, the observed feature vector Xo0 at stage 0 may comprise X10 and X20. An unobserved feature vector Xut comprises those features that are not observed. In the example of FIG. 5A, the unobserved feature vector Xu0 at stage 0 may comprise X30.).
Regarding dependent claim 20, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG further teaches wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a fully federated learning procedure, and wherein performing the fully federated learning procedure comprises alternating between training the first autoencoder and training the second autoencoder ([0095] As shown in FIG. 5A, at a first successive stage t=1, the respective VAE of that stage comprises a respective first encoder 208 p 1 and a respective first encoder 208 q 1. The first encoder 208 q 1 at stage 1 may encode from Xo1 (e.g. X21) to Z1, and the first decoder 208 q 0 at stage 1 decodes from Z1 to X1 (e.g. decoded versions of X11, X21 and X31). Note that the observed feature vector Xo1 may depend, at least in part, on the action output at stage 0, as described in more detail below; [0096] FIG. 5A also shows at least some of the stages comprising a respective second decoder network 501 p t. In the example of FIG. 5A only the initial stage 0 comprises a second decoder network 501 p 0, whereas the successive stage (stage 1) does not comprise a second decoder network. However it is not excluded that some or all of the successive stages may comprise a respective second decoder, as is the case in FIG. 5B. It is also not essential that the initial stage 0 comprises a respective second decoder. The second decoder network 501 p t of a given stage t is configured to predict one or more actions At based on the latent space representation Zt at that stage t. For instance, at stage 0, the second decoder network 501 p 0 decodes from the latent space representation Z0 to predict action(s) A0. Any given second decoder network 501 p t may predict a single action At or multiple actions At).
Regarding dependent claim 21, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 20 that is incorporated. ZHANG further teaches wherein alternating between training the first autoencoder and training the second autoencoder comprises:
performing a first plurality of training iterations associated with the first autoencoder according to a first training frequency ([0097] As mentioned above, the sequence of stages comprises one or more successive stages, and one some or all of those successive stages may comprise a respective second encoder network 501 q t. The second encoder network 501 q t is configured to encode from the predicted actions At−1 of the previous stage to the latent space representation Zt of that successive stage, i.e. the “present stage”. That is, a second encoder network 501 q t at stage t encodes from the action(s) predicted at stage t−1 to the latent space representation Zt at stage t. In the example of FIG. 5A, stage 1 comprises a second encoder network 501 q 0 that encodes actions(s) A0 to the latent space representation Z1. Each successive stage in FIG. 5A is shown as comprising a respective second encoder network 501 q t, but it will be appreciated that this is just one of several possible implementations); and
performing a second plurality of training iterations associated with the second autoencoder according to a second training frequency that is higher than the first training frequency ([0099] Each successive stage further comprises a sequential network 502 configured to transform the latent space representation Zt of a previous stage into a latent space representation Zt of a present stage. That is, stage t comprises a sequential network 502 that transforms (i.e. maps) from the latent space representation Zt−1 at stage t−1 to the latent space representation Zt at stage t. In the example of FIG. 5A, stage 1 comprises a sequential network 502 that transforms from latent space representation Z0 to latent space representation Z1. In this example, Z1 is dependent on both Z0 and A0. The sequential network 502 may also be referred to as a linking network, or a latent space linking network. A linking network links (i.e. maps) one representation to another. In this case, a preceding latent space representation is linked to a succeeding latent space representation. In practice, any suitable neural network may be used as the sequential network 502).
Regarding dependent claim 22, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG further teaches wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises:
providing an observed environmental vector to a server ([0052] the interface 204 is thus arranged to gather observations (i.e. observed values) of various features of an input feature space. It may for example be arranged to collect inputs entered by one or more users via a UI front end, e.g. microphone, touch screen, etc.; or to automatically collect data from unmanned devices such as sensor devices. The logic of the interface may be implemented on a server, and arranged to collect data from one or more external user devices such as user devices or sensor devices. Alternatively some or all of the logic of the interface 204 may also be implemented on the user device(s) or sensor devices its/themselves); and
receiving the first autoencoder from the server, wherein the first autoencoder is based at least in part on the observed environmental vector ([0054] The machine learning (ML) algorithm 206 comprises a machine-learning model 208, comprising one or more constituent neural networks 101. A machine-leaning model 208 such as this may also be referred to as a knowledge model. The machine learning algorithm 206 also comprises a learning function 209 arranged to tune the weights w of the nodes 104 of the neural network(s) 101 of the machine-learning model 208 according to a learning process, e.g. training based on a set of training data).
Regarding dependent claim 23, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 22 that is incorporated. ZHANG further teaches wherein the first autoencoder is based at least in part on at least one additional environmental vector associated with at least one additional client ([0057] as shown in FIG. 1B, at some or all of the nodes 104 in the network 101, the respective weight may be modelled as a probabilistic distribution such as a Gaussian. In such cases the neural network 101 is sometimes referred to as a Bayesian neural network. Optionally, the value input/output on each of some or all of the edges 106 may each also be modelled as a respective probabilistic distribution. For any given weight or edge, the distribution may be modelled in terms of a set of samples of the distribution, or a set of parameters parameterizing the respective distribution, e.g. a pair of parameters specifying its centre point and width (e.g. in terms of its mean μ and standard deviation σ or variance σ2). The value of the edge or weight may be a random sample from the distribution. The learning or the weights may comprise tuning one or more of the parameters of each distribution).
Regarding dependent claim 24, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG further teaches wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises:
updating the second autoencoder to determine a set of updated neural network parameters ([0144] We proposed to pre-train both the generative and inference models offline before learning the RL policies. In this case, we assume the access to the unobserved features, so that we can construct a supervised learning task to learn to impute unobserved features. Concretely, the pre-training task update the parameters θ, ϕ by maximizing the following variational lower-bound); and
transmitting the set of updated neural network parameters to a server ([0145] By incorporating the term log pθ(xt u|zt), the training of sequential VAE generalizes from an unsupervised task to a supervised task that learns the model dynamics from past observed transitions and imputes the missing features. Given the pre-trained representation learning model, the policy is trained under multi-stage reinforcement learning setting, where the representation provided by sequential VAE is taken as the input to the policy).
Regarding dependent claim 25, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG further teaches wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises:
performing a first plurality of training iterations associated with the first autoencoder according to a first training frequency ([0097] As mentioned above, the sequence of stages comprises one or more successive stages, and one some or all of those successive stages may comprise a respective second encoder network 501 q t. The second encoder network 501 q t is configured to encode from the predicted actions At−1 of the previous stage to the latent space representation Zt of that successive stage, i.e. the “present stage”. That is, a second encoder network 501 q t at stage t encodes from the action(s) predicted at stage t−1 to the latent space representation Zt at stage t. In the example of FIG. 5A, stage 1 comprises a second encoder network 501 q 0 that encodes actions(s) A0 to the latent space representation Z1. Each successive stage in FIG. 5A is shown as comprising a respective second encoder network 501 q t, but it will be appreciated that this is just one of several possible implementations), wherein performing a training iteration of the first plurality of training iterations comprises:
providing an observed environmental vector to a server ([0052] the interface 204 is thus arranged to gather observations (i.e. observed values) of various features of an input feature space. It may for example be arranged to collect inputs entered by one or more users via a UI front end, e.g. microphone, touch screen, etc.; or to automatically collect data from unmanned devices such as sensor devices. The logic of the interface may be implemented on a server, and arranged to collect data from one or more external user devices such as user devices or sensor devices. Alternatively some or all of the logic of the interface 204 may also be implemented on the user device(s) or sensor devices its/themselves); and
receiving an updated first autoencoder from the server, wherein the updated first autoencoder is based at least in part on the observed environmental vector ([0054] The machine learning (ML) algorithm 206 comprises a machine-learning model 208, comprising one or more constituent neural networks 101. A machine-leaning model 208 such as this may also be referred to as a knowledge model. The machine learning algorithm 206 also comprises a learning function 209 arranged to tune the weights w of the nodes 104 of the neural network(s) 101 of the machine-learning model 208 according to a learning process, e.g. training based on a set of training data); and
performing a second plurality of training iterations associated with the second autoencoder according to a second training frequency that is higher than the first training frequency ([0099] Each successive stage further comprises a sequential network 502 configured to transform the latent space representation Zt of a previous stage into a latent space representation Zt of a present stage. That is, stage t comprises a sequential network 502 that transforms (i.e. maps) from the latent space representation Zt−1 at stage t−1 to the latent space representation Zt at stage t. In the example of FIG. 5A, stage 1 comprises a sequential network 502 that transforms from latent space representation Z0 to latent space representation Z1. In this example, Z1 is dependent on both Z0 and A0. The sequential network 502 may also be referred to as a linking network, or a latent space linking network. A linking network links (i.e. maps) one representation to another. In this case, a preceding latent space representation is linked to a succeeding latent space representation. In practice, any suitable neural network may be used as the sequential network 502).
Regarding dependent claim 26, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 11 that is incorporated. ZHANG and Ye further teach wherein training the at least one of the first autoencoder or the second autoencoder comprises performing a partial federated learning procedure, and wherein performing the partial federated learning procedure comprises:
receiving, from a server, a set of neural network parameters associated with the first autoencoder and the second autoencoder (ZHANG [0054] The machine learning (ML) algorithm 206 comprises a machine-learning model 208, comprising one or more constituent neural networks 101. A machine-leaning model 208 such as this may also be referred to as a knowledge model. The machine learning algorithm 206 also comprises a learning function 209 arranged to tune the weights w of the nodes 104 of the neural network(s) 101 of the machine-learning model 208 according to a learning process, e.g. training based on a set of training data);
obtaining an observed environmental training vector (ZHANG [0007] During a training phase, experience data comprising a large number of input data points X is supplied to the neural network, each data point comprising an example set of values for the feature vector);
inputting the observed environmental training vector to a first encoder of the first autoencoder to determine a training feature vector (ZHANG [0061] FIG. 3 shows an example data set comprising a plurality of data points i=0, 1, 2, . . . etc. Each data point i comprises a respective set of values of the feature vector (where xid is the value of the dth feature in the ith data point). The input feature vector Xi represents the input observations for a given data point; [0015] each stage in the sequence comprises: a variational auto-encoder, VAE, comprising a respective first encoder arranged to encode a respective subset of the real-world features into a respective latent space representation);
obtaining an observed wireless communication training vector (ZHANG [0068] The encoder 208q is arranged to receive the observed feature vector X.sub.o as an input);
inputting the training feature vector and the observed wireless communication training vector to a second encoder of the second autoencoder to determine a training latent vector (ZHANG [0074] FIG. 4B shows a more abstracted representation of a VAE such as shown in FIG. 4A; [0075] FIG. 4C shows an even higher level representation of a VAE such as that shown in FIGS. 4A and 4B. In FIG. 4C the solid lines represent a generative network of the decoder 208q, and the dashed lines represents an inference network of the encoder 208p. In this form of diagram, a vector shown in a circle represents a vector of distributions. So here, each element of the feature vector X (=x.sub.1 . . . x.sub.d) is modelled as a distribution, e.g. as discussed in relation to FIG. 1C. Similarly each element of the latent vector Z is modelled as a distribution. On the other hand, a vector shown without a circle represents a fixed point. So in the illustrated example, the weights θ of the generative network are modelled as simple values, not distributions (though that is a possibility as well). The rounded rectangle labelled N represents the “plate”, meaning the vectors within the plate are iterated over a number N of learning steps (one for each data point). In other words i=0, . . . , N−1. A vector outside the plate is global, i.e. it does not scale with the number of data points i (nor the number of features d in the feature vector). The rounded rectangle labelled D represents that the feature vector X comprises multiple elements x.sub.1 . . . x.sub.d));
inputting the training feature vector and the training latent vector to a second decoder of the second autoencoder to determine a second training output of the second autoencoder (ZHANG [0069] The latent vector Z is a compressed (i.e. encoded) representation of the information contained in the input observations X.sub.o. No one element of the latent vector Z necessarily represents directly any real world quantity, but the vector Z as a whole represents the information in the input data in compressed form. It could be considered conceptually to represent abstract features abstracted from the input data X.sub.o, such as “wrinklyness” and “trunk-like-ness” in the example of elephant recognition (though no one element of the latent vector Z can necessarily be mapped onto any one such factor, and rather the latent vector Z as a whole encodes such abstract information). The decoder 208p is arranged to decode the latent vector Z back into values in a real-world feature space, i.e. back to an uncompressed form {circumflex over (X)} representing the actual observed properties (e.g. pixel values). The decoded feature vector {circumflex over (X)} has the same number of elements representing the same respective features as the input vector X.sub.o.);
determining a loss associated with the second autoencoder based at least in part on the second training output, wherein the loss is associated with the set of neural network parameters (Ye, page 3, Section III END-TO-END COMMUNICATION SYSTEM “The crossentropy loss is computed at the receiver, which is defined as L = ∑ M n=1 −sn log(ˆsn), (3) where sn and sˆn represent the nth elements of s and ˆs, respectively”);
determining a plurality of gradients of the loss with respect to a set of autoencoder parameters, wherein the set of autoencoder parameters corresponds to the second autoencoder (Ye, page 2, Section II. MODELING CHANNEL WITH CONDITIONAL GAN “a GAN is applied to model the distribution of the channel output and the learned model is then used as a surrogate of the real channel when training the transmitter so that the gradients can pass through to the transmitter.”; Ye, page 3, Section III END-TO-END COMMUNICATION SYSTEM “With the conditional GAN, the gradients can be backpropagated to the transmitter”; Ye, page 4, Section A. Training Receiver “The receiver can be trained easily since the loss function is computed at the receiver, thus the gradients of the loss can be easily obtained”);
updating the set of autoencoder parameters based at least in part on the plurality of gradients (ZHANG [0071] With each data point in the training data (each data point in the experience data during learning), the learning function 209 tunes the weights ø and θ so that the VAE 208 learns to encode the feature vector X into the latent space Z and back again; [0072] For instance, this may be done by minimizing the Kullback-Leibler (KL) divergence between qø(Zi|Xi) and pθ(Xi|Zi). The minimization may be performed using an optimization function such as an ELBO (evidence lower bound) function, which uses cost function minimization based on gradient descent);
updating the set of autoencoder parameters a specified number of times to determine a final set of updated autoencoder parameters (ZHANG [0144] We proposed to pre-train both the generative and inference models offline before learning the RL policies. In this case, we assume the access to the unobserved features, so that we can construct a supervised learning task to learn to impute unobserved features. Concretely, the pre-training task update the parameters θ, ϕ by maximizing the following variational lower-bound); and
transmitting the final set of updated autoencoder parameters to the server (ZHANG [0145] By incorporating the term log pθ(xt u|zt), the training of sequential VAE generalizes from an unsupervised task to a supervised task that learns the model dynamics from past observed transitions and imputes the missing features. Given the pre-trained representation learning model, the policy is trained under multi-stage reinforcement learning setting, where the representation provided by sequential VAE is taken as the input to the policy).
Regarding independent claim 27, ZHANG teaches a method
receiving, from a client, a feature vector associated with one or more features associated with an environment of the client ([0048] FIG. 2 illustrates an example computing apparatus 200 for implementing an artificial intelligence (AI) algorithm including a machine-learning (ML) model in accordance with embodiments described herein. The computing apparatus 200 may comprise one or more user terminals, such as a desktop computer, laptop computer, tablet, smartphone, wearable smart device such as a smart watch, or an on-board computer of a vehicle such as car, etc. Additionally or alternatively, the computing apparatus 200 may comprise a server. A server herein refers to a logical entity which may comprise one or more physical server units located at one or more geographic sites. Where required, distributed or “cloud” computing techniques are in themselves known in the art. The one or more user terminals and/or the one or more server units of the server may be connected to one another via a packet-switched network, which may comprise for example a wide-area internetwork such as the Internet, a mobile cellular network such as a 3GPP network, a wired local area network (LAN) such as an Ethernet network, or a wireless LAN such as a Wi-Fi, Thread or 6LoWPAN network; [0068] The encoder 208 q is arranged to receive the observed feature vector Xo as an input and encode it into a latent vector Z (a representation in a latent space));
receiving, from the client, a latent vector that is based at least in part on the feature vector ([0068] The decoder 208p is arranged to receive the latent vector Z and decode back to the original feature space of the feature vector. The version of the feature vector output by the decoder 208p may be labelled herein X);
determining an observed wireless communication vector based at least in part on the feature vector and the latent vector ([0069] The latent vector Z is a compressed (i.e. encoded) representation of the information contained in the input observations X.sub.o. No one element of the latent vector Z necessarily represents directly any real world quantity, but the vector Z as a whole represents the information in the input data in compressed form. It could be considered conceptually to represent abstract features abstracted from the input data X.sub.o, such as “wrinklyness” and “trunk-like-ness” in the example of elephant recognition (though no one element of the latent vector Z can necessarily be mapped onto any one such factor, and rather the latent vector Z as a whole encodes such abstract information). The decoder 208p is arranged to decode the latent vector Z back into values in a real-world feature space, i.e. back to an uncompressed form {circumflex over (X)} representing the actual observed properties (e.g. pixel values). The decoded feature vector {circumflex over (X)} has the same number of elements representing the same respective features as the input vector X.sub.o.); and
performing a wireless communication action based at least in part on determining the observed wireless communication vector ([0082] In general, the sequential model may also output a set of actions to take in relation to the target. For instance, an action may include interacting with the target in one way or another. In some examples, performing an action may include observing one or more of the features. In other examples, performing an action may include implementing a task that affects the target, e.g. a task that physically affects the target. If the target is a living being, the task may mentally or physiologically affect the target. As a particular example, performing a task on a human may include performing a medical surgery on the human or supplying a medicament to the human. Note that outputting an action may comprise outputting a request or suggestion to perform the action, or in some examples, actually performing the action. For instance, the sequential model may be used to control a connected device that is configured to observe a measurement or perform a task, e.g. to supply a drug via an intravenous injection).
ZHANG does not explicitly teach a method of wireless communication performed by a server, a latent vector comprising compressed channel state feedback.
However, in the same field of endeavor, Ye teaches a method of wireless communication performed by a server (Fig. 2, Receiver; Abstract, “In this article, we use deep neural networks (DNNs) to develop an end-to-end wireless communication system, in which DNNs are employed for all signal-related functionalities, including encoding, decoding, modulation, and equalization. However, accurate instantaneous channel transfer function, i.e., the channel state information (CSI), is necessary to compute the gradient of the DNN representing. In many communication systems, the channel transfer function is hard to obtain in advance and varies with time and location. In this article, this constraint is released by developing a channel agnostic end-to-end system that does not rely on any prior information about the channel. We use a conditional generative adversarial net (GAN) to represent the channel effects, where the encoded signal of the transmitter will serve as the conditioning information. In addition, in order to obtain accurate channel state information for signal detection at the receiver (i.e. server), the received signal corresponding to the pilot data is added as a part of the conditioning information”), a latent vector comprising compressed channel state feedback (page 3, left column, 1st paragraph “… If the discriminator, D, can successfully classify the samples of the two sources, then its success will be used to generate a feed back to the generator, G, so that the generator, G, can learn to produce samples more similar to the real samples …”).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of the end-to-end communication system learning the implements of the transmitter and the receiver using DNNs as suggested in Ye into ZHANG’s system because both of these systems are addressing both the transmitter and the receiver are represented by deep neural networks (DNNs) and can be interpreted as an auto-encoder and an auto-decoder, respectively. This modification would have been motivated by the desire to develop a channel agnostic end to-end learning based communication system, where different types of channel effects can be automatically learned without knowing the specific channel transfer function (Ye, page 2, left column, 1st paragraph).
Regarding dependent claim 28, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 27 that is incorporated. ZHANG teaches wherein the feature vector is based at least in part on an observed environmental vector ([0061] FIG. 3 shows an example data set comprising a plurality of data points i=0, 1, 2, . . . etc. Each data point i comprises a respective set of values of the feature vector (where x.sub.id is the value of the d.sub.th feature in the i.sub.th data point). The input feature vector X.sub.i represents the input observations for a given data point, where in general any given observation i may or may not comprise a complete set of values for all the elements of the feature vector X).
Regarding independent claim 29, it is an apparatus claim that corresponding to the method of claim 1. Therefore, it is rejected for the same reason as claim 1 above. ZHANG further teaches one or more memories ([0050]); and one or more processors, coupled to the one or more memories, configured to perform the method of claim 1 ([0050]).
Regarding independent claim 30, it is an apparatus claim that corresponding to the method of claim 27. Therefore, it is rejected for the same reason as claim 27 above. ZHANG further teaches one or more memories ([0050]); and one or more processors, coupled to the one or more memories, configured to perform the method of claim 27 ([0050]).
Regarding dependent claim 31, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 29 that is incorporated. ZHANG further teaches wherein the first autoencoder and the second autoencoder are trained using a federated learning procedure ([0089] Referring first to FIG. 5A, at each stage t (t=0 . . . T) of the sequential model 208′, a respective VAE is trained for each of a set of observed features, e.g. X10 and X20 at stage t=0. In FIG. 5A, for a feature Xit, i indicates the feature itself, whilst t indicates the stage at which the feature is observed or generated, as the case may be. Only three features are shown here by way of illustration, but it will be appreciated that other numbers could be used. The observed features together form a respective group of the feature space. That is, each group comprises a different respective one or more of the features of the feature space. I.e. each group is a different one or more of the elements of the observed feature vector Xot. In the example of FIG. 5A, the observed feature vector Xo0 at stage 0 may comprise X10 and X20. An unobserved feature vector Xut comprises those features that are not observed. In the example of FIG. 5A, the unobserved feature vector Xu0 at stage 0 may comprise X30).
Regarding dependent claim 32, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 29 that is incorporated. ZHANG further teaches wherein the feature vector comprises information indicative of a client antenna configuration or a large scale channel characteristic ([0060] For instance, consider a simple example as in FIG. 1C where the machine-learning model comprises a single neural network 101, arranged to take a feature vector X as its input 108i and to output a classification Y as its output 108o. The input feature vector X comprises a plurality of elements x.sub.d, each representing a different feature d=0, 1, 2, . . . etc. E.g. in the example of image recognition, each element of the feature vector X may represent a respective pixel value. For instance one element represents the red channel for pixel (0,0); another element represents the green channel for pixel (0,0); another element represents the blue channel of pixel (0,0); another element represents the red channel of pixel (0,1); and so forth. As another example, where the neural network is used to make a medical diagnosis, each of the elements of the feature vector may represent a value of a different symptom of the subject, physical feature of the subject, or other fact about the subject (e.g. body temperature, blood pressure, etc.)).
Regarding dependent claim 33, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 30 that is incorporated. ZHANG further teaches wherein the server is further configured to update a model parameter based on the feature vector and latent vector ([0052] the interface 204 is thus arranged to gather observations (i.e. observed values) of various features of an input feature space. It may for example be arranged to collect inputs entered by one or more users via a UI front end, e.g. microphone, touch screen, etc.; or to automatically collect data from unmanned devices such as sensor devices. The logic of the interface may be implemented on a server, and arranged to collect data from one or more external user devices such as user devices or sensor devices. Alternatively some or all of the logic of the interface 204 may also be implemented on the user device(s) or sensor devices its/themselves; [0054] The machine learning (ML) algorithm 206 comprises a machine-learning model 208, comprising one or more constituent neural networks 101. A machine-leaning model 208 such as this may also be referred to as a knowledge model. The machine learning algorithm 206 also comprises a learning function 209 arranged to tune the weights w of the nodes 104 of the neural network(s) 101 of the machine-learning model 208 according to a learning process, e.g. training based on a set of training data).
Claims 9 and 34 are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG, in view of Ye as applied in claim 1, further in view of Wang et al. (hereinafter Wang), "The Evolution of LTE Physical Layer Control Channels," in IEEE Communications Surveys & Tutorials, vol. 18, no. 2, pp. 1336-1354, Secondquarter 2016, doi: 10.1109/COMST.2015.2510371.
Regarding dependent claim 9, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 1 that is incorporated.
The combination of ZHANG and Ye does not explicitly teach
wherein transmitting the feature vector and the latent vector comprises transmitting the feature vector and the latent vector using:
a physical uplink control channel,
a physical uplink shared channel, or
a combination thereof.
However, in the same field of endeavor, Wang teaches wherein transmitting the feature vector and the latent vector comprises transmitting the feature vector and the latent vector using: a physical uplink control channel, a physical uplink shared channel, or a combination thereof (page 1337, Section II. Control Channels and Data Transmissions, “As shown in Fig. 2, for downlink data transmissions (i.e., eNB-originated), the eNB transmits the PDSCH grant i.e., PDSCH resource assignments and their modulation and coding scheme (MCS) on PDCCH, and the data packet on the PDSCH accordingly. A UE first reads physical control format indicator channel (PCFICH, cf. Fig. 1) every subframe to determine the number of OFDM symbols occupied by the control region. The UE monitors its PDCCH in the control region to discover its grant. Once its PDCCH is detected, the UE decodes the PDSCH on the allocated resources using the MCS provided. Depending on whether the decoding is successful, the UE sends ACK or NAK on physical uplink control channel (PUCCH)”, page 1339, Section B. Physical Uplink Control Channel: PUCCH; page 1337, Section II. Control Channels and Data Transmissions, “The MAC in the base station (or eNB in LTE terminology) includes a dynamic resource scheduler that allocates physical resources on physical downlink shared channel (PDSCH) for downlink data traffic and on physical uplink shared channel (PUSCH) for uplink data traffic. The scheduler takes into account the traffic volume, the quality of service (QoS) requirement, and the radio channel conditions when sharing the physical resources among UEs. The basic transmission unit for data, i.e., the smallest resource unit that can be scheduled for transmission on the PDSCH and PUSCH is the resource block pair (henceforth referred to as RB) which consists of 12 subcarriers such that one unit lasts for a duration of one subframe (14 orthogonal frequency-division multiplexing or OFDM symbols), thereby comprising 168 resource elements (REs), as illustrated in Fig. 1”).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Physical layer control signals in cellular communications serving the purpose of delivering physical layer control messages in a timely fashion to support cell radio resource management and data transmissions between the network and the mobile users as suggested in Wang into ZHANG and Ye’s system because both of these systems are addressing transmitting vectors. This modification would have been motivated by the desire to support frequency domain ICIC, achieve improved spatial reuse of control channel resources, deliver beamforming as well as diversity, and coexist on the same carrier with legacy UEs (Wang, page 1342, bottom last right paragraph).
Regarding dependent claim 34, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 30 that is incorporated. ZHANG further teaches wherein the wireless communication action comprises selection of a modulation scheme or waveform for subsequent communication with the client.
The combination of ZHANG and Ye does not explicitly teach wherein the wireless communication action comprises selection of a modulation scheme or waveform for subsequent communication with the client.
However, in the same field of endeavor, Wang teaches wherein the wireless communication action comprises selection of a modulation scheme or waveform for subsequent communication with the client (page 1337; Section II. CONTROL CHANNELS AND DATA TRANSMISSIONS, 2nd paragraph, As shown in Fig. 2, for downlink data transmissions (i.e., eNB-originated), the eNB transmits the PDSCH grant i.e., PDSCH resource assignments and their modulation and coding scheme (MCS) on PDCCH, and the data packet on the PDSCH accordingly. A UE first reads physical control format indicator channel (PCFICH, cf. Fig. 1) every subframe to determine the number of OFDM symbols occupied by the control region. The UE monitors its PDCCH in the control region to discover its grant. Once its PDCCH is detected, the UE decodes the PDSCH on the allocated resources using the MCS provided, 3rd paragraph, For uplink data transmissions (i.e., UE-originated), a UE sends a scheduling request (SR) to an eNB via PUCCH if the PUCCH resource is already assigned. If a PUCCH is not configured for the UE, the UE sends the request through the physical random access channel (PRACH), and then monitors the PDCCH for the PUSCH resource assignments. The eNB receives the SR and assigns PUSCH resources and the associated MCS via PDCCH; page 1339, Section B. Physical Uplink Control Channel: PUCCH, PUCCH is therefore transmitted on one RB to allow for the transmission in the single carrier frequency division multiplexing (SC-FDM) waveform [15]. For the purpose of maximizing the frequency diversity, half of the PUCCHRB (i.e.,12 subcarriers by 7 OFDM symbols) is placed at or near the edge of the system bandwidth, the other half at the opposite edge as illustrated in Fig. 4).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of Physical layer control signals in cellular communications serving the purpose of delivering physical layer control messages in a timely fashion to support cell radio resource management and data transmissions between the network and the mobile users as suggested in Wang into ZHANG and Ye’s system because both of these systems are addressing transmitting vectors. This modification would have been motivated by the desire to support frequency domain ICIC, achieve improved spatial reuse of control channel resources, deliver beamforming as well as diversity, and coexist on the same carrier with legacy UEs (Wang, page 1342, bottom last right paragraph).
Claims 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over ZHANG, in view of Ye as applied in claim 14, further in view of Haidar et al. (hereinafter Haidar), US 20200134415 A1.
Regarding dependent claim 15, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 14 that is incorporated. the combination of ZHANG and Ye does not explicitly teach wherein the first loss function comprises a first reconstruction loss and a first regularization term for the first autoencoder, and wherein the second loss function comprises a second reconstruction loss and a second regularization term for the second autoencoder.
However, in the same field of endeavor, Haidar teaches wherein the first loss function comprises a first reconstruction loss and a first regularization term for the first autoencoder, and wherein the second loss function comprises a second reconstruction loss and a second regularization term for the second autoencoder ([0035] To train the autoencoder-based GAN 400, three objective functions are utilized: (1) the reconstruction loss functions for the autoencoder 420 with the regularization term to penalize the output of the decoder neural network 410 if the representation output by decoder gets close to a one-hot representation; [0036]).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of the training of the encoder neural network and the training the decoder neural network comprising calculating a reconstruction loss based on a difference between the one-hot representation of the real text and the reconstructed softmax representation of the real text from the decoder neural network as suggested in Haidar into ZHANG and Ye’s system because both of these systems are addressing optimizing the loss function. This modification would have been motivated by the desire for more efficient and robust techniques for training a GAN for NLP applications (Haidar, [0004]).
Regarding dependent claim 16, the combination of ZHANG and Ye teaches all the limitations as set forth in the rejection of claim 14 that is incorporated. the combination of ZHANG and Ye does not explicitly teach wherein the first autoencoder and the second autoencoder are regular autoencoders, and wherein the variational lower bound function does not include a regularization term.
However, in the same field of endeavor, Haidar teaches wherein the first autoencoder and the second autoencoder are regular autoencoders ([0031] FIG. 4 illustrates a diagram of an autoencoder-based GAN 400 for text generation, according to some embodiments. The GAN autoencoder-based 400 may execute on one or more processing units described above. The autoencoder-based GAN 400 includes a generator artificial neural network 402 (hereinafter generator 402) and a discriminator artificial neural network 404 (hereinafter discriminator 404). The autoencoder-based GAN 400 further includes an autoencoder 420, which comprises an encoder artificial neural network 408 (hereinafter encoder neural network 408) and a decoder artificial neural network 410 (hereinafter decoder neural network 410)), and wherein the variational lower bound function does not include a regularization term ([0035] To train the autoencoder-based GAN 400, three objective functions are utilized: … (3) the generator 402 to be adversarially trained to the discriminator 404; [0039] To minimize the adversarial loss between the discriminator neural network 404 and the generator neural network 402, the autoencoder-based. GAN 400 further utilizes the following equation when the generator neural network 402 and the discriminator neural network 404 are adversarially trained).
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the teaching of the training of the encoder neural network and the training the decoder neural network comprising calculating a reconstruction loss based on a difference between the one-hot representation of the real text and the reconstructed softmax representation of the real text from the decoder neural network as suggested in Haidar into ZHANG and Ye’s system because both of these systems are addressing optimizing the loss function. This modification would have been motivated by the desire for more efficient and robust techniques for training a GAN for NLP applications (Haidar, [0004]).
Response to Arguments
Applicant's arguments filed 02/17/2026 have been fully considered. Each of applicant’s remarks is set forth, followed by examiner’s response.
(1) Regarding to 35 U.S.C 101 rejection, Applicant alleges that claim 1 recites "determining, using a first autoencoder, a feature vector associated with one or more features associated with an environment of the client," "determining a latent vector comprising compressed channel state feedback using a second autoencoder and based at least in part on the feature vector," and "transmitting the feature vector and the latent vector." The claim requires execution of trained neural network parameters in a first autoencoder and a second autoencoder. A human mind cannot perform layered neural network transformations using trained model parameters to generate "a latent vector comprising compressed channel state feedback." The claim recites operation of neural network architectures within a wireless communication system, not a mental process. Claim 8 recites "receiving a channel state information (CSI) reference signal (CSI-RS)" and "determining CSI based at least in part on the CSI-RS." The specification states that "the observed wireless communication vector, x, may comprise a propagation channel that the client estimates based at least in part on a received CSI-RS." These are physical layer wireless communication operations.
As to point (1), Examiner respectfully disagrees. According to MPEP § 2106.04(II)(A)(1), in Step 2A, Prong One, this part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim. As discussed in the rejection above, the claim is directed to an abstract idea that encompasses mental processes including evaluations or observations that are practically capable of being performed in the human mind with the assistance of pen and paper. The claim places no limits on how the steps are performed. That is, nothing in the claim element precludes the step from practically being performed in the mind. The limitations of a method of wireless communication performed by client; An apparatus for wireless communication at a client, comprising: a one or more memories; and one or more processors, coupled to the one or more memories are recited at a high level of generality and are recited as performing generic computer function routinely used in computer applications. Generic computer components recited as performing generic computer functions that are well-understood, routine and conventional activities amount to no more than implementing the abstract idea with a computerized system. The limitation of receiving a channel state information (CSI) reference signal (CSI-RS) is recited at a high level of generality, and amounts to mere data inputting, which is a form of insignificant extra-solution activity (see MPEP § 2106.05(g)). Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(2) Applicant further argues that Claim 27 recites "performing a wireless communication action based at least in part on determining the observed wireless communication vector." The claims therefore operate within a wireless communication system and are used to perform a wireless communication action. They are integrated into a practical application.
As to point (2), the step of "performing a wireless communication action based at least in part on determining the observed wireless communication vector" is recited at a high level of generality, and amounts to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer (see MPEP § 2106.05(f)). One way to determine integration into a practical application is when the claimed invention improves the functioning of a computer or improves another technology or technical field. To evaluate an improvement to a computer or technical field, the specification must set forth an improvement in technology and the claim itself must reflect the disclosed improvement. See MPEP 2106.04(d)(1) and 2106.05(a). The consideration of whether the claim as a whole includes an improvement to a computer or to a technological field requires an evaluation of the specification and the claim to ensure that a technical explanation of the asserted improvement is present in the specification, and that the claim reflects the asserted improvement. While the claims operate within a wireless communication system and are used to perform a wireless communication action, there is no improvement to the functioning of a computer nor to any other technology. At best, the claimed combination amounts to an improvement to the abstract idea rather than to any technology. See MPEP 2106.05(a). Any purported improvements are provided by the judicial exception alone, i.e. mental process, thus the claim as a whole does not integrate the judicial exception into a practical application nor provide significantly more than the judicial exception. Thus, the claims are patent ineligible and are rejected under 35 U.S.C. 101 as detailed in the rejections set forth above.
(3) Regarding Step 2B, Applicant argues the claims recite a specific ordered combination of elements operating within a wireless communication system, including "a first autoencoder," "a second autoencoder," determining "a feature vector associated with one or more features associated with an environment of the client," determining "a latent vector comprising compressed channel state feedback using a second autoencoder and based at least in part on the feature vector," "transmitting the feature vector and the latent vector," and performing "a wireless communication action based at least in part on determining the observed wireless communication vector." Certain dependent claims further recite "performing a fully federated learning procedure" and "performing a partial federated learning procedure." These elements define a particular machine learning architecture integrated into a wireless communication system. The claims do not merely recite generic data processing or result-oriented functional language. Rather, they require the use of paired autoencoders, the conditioning of a second autoencoder on a feature vector associated with an environment of the client, the generation and transmission of specific vectors, and the performance of a wireless communication action based at least in part on reconstructed channel state information. The specification states that "autoencoder pairs may be trained using federated learning." The specification further explains that "Federated learning is a machine learning technique that enables multiple clients to collaboratively learn neural network models, while the server does not collect the data from the clients." The specification further states that "partial federated learning and/or fully federated learning techniques may be used to provide and train personalized autoencoder models adapted for respective clients." These disclosures reflect that the claimed architecture is not a generic computer implementation of an abstract idea, but rather a specific machine learning configuration applied within a wireless communication framework.
As to point (3), this part of the eligibility analysis evaluates whether the claim as a whole amounts to significantly more than the recited exception i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP 2106.05. As explained with respect to Step 2A, Prong Two, these additional elements were found to be insignificant extra-solution activity in Step 2A, Prong Two, because they were determined to be insignificant limitations as necessary data gathering and outputting. As discussed in Step 2A, Prong Two above, the recitations of “performing a wireless communication action based at least in part on determining the observed wireless communication vector” is recited at a high level of generality. The elements “transmitting the feature vector and the latent vector”, “receiving, from a client, a feature vector associated with one or more features associated with an environment of the client”, “receiving, from the client, a latent vector that is based at least in part on the feature vector” amount to receiving or transmitting data over a network and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II. As discussed in Step 2A, Prong Two above, a method of wireless communication performed by client; An apparatus for wireless communication at a client, comprising: one or more memories; and one or more processors, coupled to the one or more memories amount to no more than mere instructions to apply the exception using a generic computer component. Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept. (Step 2B: NO).
(4) Applicant alleges that USPTO Example 47 explains that claims reciting specific artificial intelligence architectures and their application to a technological field are patent eligible when the claims, as a whole, reflect an improvement to a technological process. The present claims recite specific autoencoder architectures used within a wireless communication system to generate compressed channel state feedback and to perform a wireless communication action. The specification explains that these techniques "may facilitate better physical layer link performance." Under the principles reflected in Example 47, the claims are patent eligible.
As to point (4), one way to determine integration into a practical application is when the claimed invention improves the functioning of a computer or improves another technology or technical field. To evaluate an improvement to a computer or technical field, the specification must set forth an improvement in technology and the claim itself must reflect the disclosed improvement. See MPEP 2106.04(d)(1) and 2106.05(a). The consideration of whether the claim as a whole includes an improvement to a computer or to a technological field requires an evaluation of the specification and the claim to ensure that a technical explanation of the asserted improvement is present in the specification, and that the claim reflects the asserted improvement. While the claims recite specific autoencoder architectures used within a wireless communication system to generate compressed channel state feedback and to perform a wireless communication action, there is no improvement to the functioning of a computer nor to any other technology. At best, the claimed combination amounts to an improvement to the abstract idea rather than to any technology. See MPEP 2106.05(a). Any purported improvements are provided by the judicial exception alone, i.e. mental process, thus the claim as a whole does not integrate the judicial exception into a practical application nor provide significantly more than the judicial exception. Thus, the claims are patent ineligible and are rejected under 35 U.S.C. 101 as detailed in the rejections set forth above.
(5) Regarding rejection under 35 U.S.C. 103 based on ZHANG and YE, Applicant alleges that YE does not disclose at least "determining a latent vector comprising compressed channel state feedback using a second autoencoder and based at least in part on the feature vector," as recited in amended claim 1.
As to point (5), Applicant is reminded that claim 1 is rejected using the combination of ZHANG and Ye. However, in the response, applicant against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Examiner notes that the claims place no limitations on what a compressed channel state feedback is/comprises or how the compressed channel state feedback is generated. Thus, Ye is considered to teach the latent vector comprises compressed channel state feedback.
Similar arguments have been presented for independent claims 27, 29 and 30 and thus, Applicant’s arguments are not persuasive for the same reasons.
Accordingly, claims 1-34 are rejected as set forth above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Applicant is required under 37 C.F.R. § 1.111(c) to consider these references fully when responding to this action.
Wen et al. (US 20200220593 A1) discloses communication systems and codec techniques, and, more particularly, to a communication system and a codec method based on deep learning and known channel state information.
It is noted that any citation to specific pages, columns, lines, or figures in the prior art references and any interpretation of the references should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. In re Heck, 699 F.2d 1331, 1332-33, 216 U.S.P.Q. 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1009, 158 U.S.P.Q. 275, 277 (C.C.P.A. 1968)).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AMY P HOANG whose telephone number is (469)295-9134. The examiner can normally be reached M-TH 8:30-5:00PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, JENNIFER WELCH can be reached at 571-272-7212. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AMY P HOANG/ Examiner, Art Unit 2143
/JENNIFER N WELCH/ Supervisory Patent Examiner, Art Unit 2143
Prosecution Insights