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 .
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are:
“task input gateway in claim 1.
“task feature extraction engine” in claim 1.
“replay buffer configured to” in claim 1.
“task classification engine” in claim 1, 2, 3, 4, 6, 7, 10, 11, 12, 13.
“output module configured to” in claim 1.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1
According to the first part of the analysis, in the instant case, claims 1-18 are directed to a system and claims 18-20 are directed to a method. Thus, each of the claims falls within one of the four statutory categories (i.e. process, machine, manufacture, or composition of matter).
Claim 1 recites:
Step 2A, Prong 1
“a task feature extraction engine arranged to process the received task samples and extract task invariant and task variant features” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can process features extracted from tasks. (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
“a task classification engine arranged to perform a task relation process to determine task relations between tasks, wherein the task relations are based at least partly on a subset of previous tasks accessed from the replay buffer” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can determine relations between tasks. (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“a task input gateway arranged to receive a series of task samples” (insignificant extra-solution activity)
“a task feature extraction engine arranged” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
“a replay buffer configured to store a subset of previous tasks as a representative of previous tasks that were processed by the system” (insignificant extra-solution activity)
“a task classification engine arranged to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
“an output module configured to output the task relations to be used on continual learning” (insignificant extra-solution activity)
“wherein the replay buffer is updated by storing a subset of the outputs” (insignificant extra-solution activity)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“a task input gateway arranged to receive a series of task samples” (This step appears to be directed to transmitting or receiving information, which is well-understood, routine, and conventional. i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); See MPEP 2106.05 (d) (II).)
“a task feature extraction engine arranged” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
“a replay buffer configured to store a subset of previous tasks as a representative of previous tasks that were processed by the system” (MPEP 2106.05(d)(II) indicate that merely “iv. Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93;” is a well‐understood, routine, conventional function when it is claimed in a merely generic manner (as it is in the present claim). Thereby, a conclusion that the claimed retrieving step is well-understood, routine, conventional activity is supported under Berkheimer.)
“a task classification engine arranged to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
“an output module configured to output the task relations to be used on continual learning” (This step appears to be directed to transmitting or receiving information, which is well-understood, routine, and conventional. i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); See MPEP 2106.05 (d) (II).)
“wherein the replay buffer is updated by storing a subset of the outputs” (MPEP 2106.05(d)(II) indicate that merely “iv. Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93;” is a well‐understood, routine, conventional function when it is claimed in a merely generic manner (as it is in the present claim). Thereby, a conclusion that the claimed retrieving step is well-understood, routine, conventional activity is supported under Berkheimer.)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 2 recites:
Step 2A, Prong 1
“wherein the task classification engine is configured to decouple task invariant features and task variant features based on the task relations” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can separate features based on task relations with the help of paper and pencil. (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 3 recites:
Step 2A, Prong 1
“capture inner task relations based on processing the task invariant and task invariant features, construct cross task relations based on the subset of previous tasks accessed from the replay buffer.” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can determine inner task relations based on features and cross task relations based on previous tasks (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2 & 2B
This claim does not address any additional elements not already addressed.
Claim 4 recites:
Step 2A, Prong 1
“wherein the task classification engine is configured to decouple task invariant features and task variant features based at least one of the inner task relations and cross task relations” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can separate features based on a relationship across tasks (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 5 recites:
Step 2A, Prong 1
“determine contrastive learning pairs, wherein the inner task relations and the cross task relations are defined by the determined contrastive learning pairs” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can determine contrastive learning pairs (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2 & 2B
This claim does not address any additional elements not already addressed.
Claim 6 recites:
Step 2A, Prong 1
“wherein the task classification engine is configured to determine multiple contrasts to decompose task invariant features and task variant features” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can determine contrasts to decompose features (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 7 recites:
Step 2A, Prong 1
“wherein the task classification engine is configured to determine three types of contrast to decompose task invariant features and task variant features” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can determine three types of contrast to decompose a task (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 8 recites:
Step 2A, Prong 1
“a task invariant feature extractor configured to extract task invariant features from the received series of task samples, a task variant feature extractor configured to extract task variant features from the received series of task samples” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can extract features from tasks (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“a task invariant feature extractor configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“a task invariant feature extractor configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 9 recites:
Step 2A, Prong 1
“extract task invariant and task variant features by applying at least one or more constraints wherein the constraints comprise: establishing a boundary between the invariant and variant features generating similar task invariant features across tasks establishing distinct boundaries between task variant features from each task or class” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can extract features by determining a boundary between the features (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 10 recites:
Step 2A, Prong 1
“determining an orthogonal distance loss function, applying the orthogonal distance loss function to the identified task invariant and task variant features, determining contrastive learning pairs of features, utilise the learning pairs to further decouple the task invariant and task variant features” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can determine a distance and a contrastive learning pair (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 11 recites:
Step 2A, Prong 1
“determine inner task relations, wherein the inner task relations are determined based on the learning pairs that decouple the task invariant and task variant features while clustering the invariant features together regardless of class” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can determine inner task relations based on learning pairs (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 12 recites:
Step 2A, Prong 1
“determine learning pairs of task variant features for each defined class” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can determine learning pairs of task features (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“wherein the task classification engine is further configured to: apply a classifier to the task variant features wherein the classifier is configured to group task variant features for a particular class together,” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“wherein the task classification engine is further configured to: apply a classifier to the task variant features wherein the classifier is configured to group task variant features for a particular class together,” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 13 recites:
Step 2A, Prong 1
“extract a feature of a sample of previous tasks from the replay buffer, determine additional updated learning pairs of task variant features, task invariant features and task invariant and variant features based on the feature from the replay buffer, determine a cross task relations based on the updated learning pairs” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can extract features and determine cross task relations based on learning pairs (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“wherein the task classification engine is configured to” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 14 recites:
Step 2A, Prong 1
“wherein the cross task relations are defined by learning pairs, wherein the learning pairs comprise np, pp, and vp, wherein np is a set of learning pairs between task invariant and task variant features, pp is a set of learning pairs from task invariant features, and vp represents learning pairs of task variant features, and; wherein each set of learning pairs comprises additional terms, np include extra learning pairs
PNG
media_image1.png
73
335
media_image1.png
Greyscale
and vp includes negative pairs (xp,c=i',xp,m'), wherein m represents a feature from the replay buffer” (mathematical concept).
Step 2A, Prong 2 & 2B
This claim does not address any additional elements not already addressed.
Claim 15 recites:
Step 2A, Prong 1
“wherein the cross task relations are defined by learning pairs, wherein the learning pairs comprise np, pp, and vp, wherein np is a set of learning pairs between task invariant and task variant features, pp is a set of learning pairs from task invariant features, and vp represents learning pairs of task variant features, and; wherein each set of learning pairs comprises additional terms, np include extra learning pairs (xs,c=i',xp,m'), pp includes (xs,c=i',xs,m') and vp includes negative pairs (xp,c=i',xp,m'), wherein m represents a feature from the replay buffer” (mathematical concept).
Step 2A, Prong 2 & 2B
This claim does not address any additional elements not already addressed.
Claim 16 recites:
Step 2A, Prong 1
“wherein the modelling task features comprise identifying task invariant and task variant features based on the inner task relations and cross task relations, wherein the system provides a model for learning based on resolving tasks into task invariant features and task variant features” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can identify task features based on cross task relations (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2 & 2B
This claim does not address any additional elements not already addressed.
Claim 17 recites:
Step 2A, Prong 1
“a classifier arranged to classify tasks based on a specific class a discriminator arranged to discriminate the differentiate between the task invariant and variant features of each task” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can classify tasks based on specific classes arranged by the discriminator (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“a classifier arranged” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“a classifier arranged” (mere instructions to apply the exception using a generic computer component. See 2106.05(f).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 18 recites:
Step 2A, Prong 1
“extract task invariant and task variant features from the received task samples” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can extract features from tasks (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
“performing a task relation process to: capture inner task relations based on processing the task invariant and task invariant features, construct cross task relations based on the subset of previous tasks accessed from the replay buffer” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can determine task relations based on features and cross task relations based on previous tasks (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
“decouple task invariant features and task variant features based at least one of the inner task relations and cross task relations” (This step is a recitation of a mental process that is practical to perform in the human mind. A human can separate features with the aid of paper and pen (i.e., observation, evaluation, judgement, opinion). See MPEP § 2106.04(a)(2), subsection III.).
Step 2A, Prong 2
“receiving one or more task samples” (insignificant extra-solution activity)
“receiving a subset of previous tasks from a replay buffer” (insignificant extra-solution activity)
The claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application.
Step 2B
“receiving one or more task samples” (This step appears to be directed to transmitting or receiving information, which is well-understood, routine, and conventional. i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); See MPEP 2106.05 (d) (II).) “receiving a subset of previous tasks from a replay buffer” (This step appears to be directed to transmitting or receiving information, which is well-understood, routine, and conventional. i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); See MPEP 2106.05 (d) (II).)
The additional elements, taken individually and in combination, do not result in the claim, as a whole, amounting to significantly more than the identified judicial exception”.
Claim 19 recites:
Step 2A, Prong 1
“extracting task invariant and task variant features by applying at least one or more constraints wherein the constraints comprise: establishing a boundary between the invariant and variant features generating similar task invariant features across tasks establishing distinct boundaries between task variant features from each task or class” (mental process)
Step 2A, Prong 2 & 2B
This claim does not address any additional elements not already addressed.
Claim 20 recites:
Step 2A, Prong 1
“determining the inner task relations based on the learning pairs that decouple the task invariant and task variant features while clustering the invariant features together regardless of class, grouping task variant features for a particular class together, determining learning pairs of task variant features for each defined class. extracting a feature of a sample of previous tasks from the replay buffer, determining additional updated learning pairs of task variant features, task invariant features and task invariant and variant features based on the feature from the replay buffer, and; determining a cross task relations based on the updated learning pairs” (mental process)
Step 2A, Prong 2 & 2B
This claim does not address any additional elements not already addressed.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 18-19 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Ebrahimi et al. (“Adversarial Continual Learning”).
Regarding Claim 18,
Ebrahimi teaches a computer implemented method for modelling task features for continual learning comprising the steps of:
receiving one or more task samples (pg. 2; " Factorizing task-specific and task-invariant features in our method (ACL) while learning T sequential tasks at a time.”),
extract task invariant and task variant features from the received task samples (pg. 1-2; “In this paper, we propose a novel adversarial continual learning (ACL) method in which a disjoint latent space representation composed of task-specific or private latent space is learned for each task and a task-invariant or shared feature space is learned for all tasks to enhance better knowledge transfer as well as better recall of the previous tasks.”. Task specific (i.e. variant). Task invariant (i.e. invariant). Pg. 5; “In particular, we would like to disentangle the latent space into the information shared across all tasks (zS) and the independent or private information of each task (zP) which are as distinct as possible while their concatenation followed by a task-specific head outputs the desired targets.”),
receiving a subset of previous tasks from a replay buffer (pg. 3, section 2.1; “The performance on previous tasks is preserved by storing the learned module while accommodating new tasks by augmenting the network with new modules.” Pg. 3, section 2.1; “In this work, we explicitly store raw samples into a very tiny memory used for replay buffer and we differ from prior work by how these stored exam ples are used by specific parts of our model (discriminator and shared module) to prevent forgetting in the features found to be shared across tasks.”), performing a task relation process to:
capture inner task relations based on processing the task invariant and task invariant features, construct cross task relations based on the subset of previous tasks accessed from the replay buffer (pg. 2; “The shared module, however, is significantly less susceptible to forgetting and we only use the replay buffer mechanism in this space to the extend that factorization is not perfect, i.e., when tasks have little overlap or have high domain shift in between, using a tiny memory containing samples stored from prior tasks will help with better factorization and hence higher performance.” “pg. 4-5; “We aim to achieve this by learning a disjoint latent space representation composed of a task-specific latent space for each task and a task-invariant feature space for all tasks to enhance better knowledge transfer as well as better catastrophic forgetting avoidance of prior knowledge. We mitigate catastrophic forgetting in each space differently. For the task-invariant feature space, we assume a limited memory budget of Mk which stores m samples xi=1···m ∼ Dtr j=1···k−1 from every single task prior to k.”), and;
decouple task invariant features and task variant features based at least one of the inner task relations and cross task relations (pg. 6, section 3.1; “The main insight to our approach is decoupling the conventional single representation learned for a sequence of tasks into two parts: a part that must not change because it contains task-specific features without which complete performance retrieval is not possible, and a part that is less prone to change as it contains the core structure of all tasks.”).
Regarding Claim 19,
Ebrahimi teaches a computer implemented method as per claim 18, wherein the method comprises the additional step of: extracting task invariant and task variant features by applying at least one or more constraints wherein the constraints comprise:
establishing a boundary between the invariant and variant features generating similar task invariant features across tasks establishing distinct boundaries between task variant features from each task or class (pg. 2; “To disentangle the features associated with each task, we propose a novel adversarial learning approach to enforce the shared features to be task-invariant and employ orthogonality constraints [30] to enforce the shared features to not appear in the task-specific space” pg. 5; “To this end, we introduce a mapping called Shared (SθS : X → zS) and train it to generate features that fool an adversarial discriminator D. Conversely, the adversarial discriminator (DθD : zS → T ) attempts to classify the generated features by their task labels (Tk∈{0,···,T}) .”).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 1-4, 8-9, and 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over Choi et al. (US-20230244951-A1) in view of Ebrahimi et al. (“Adversarial Continual Learning”).
Regarding Claim 1,
Choi (US 20230244951 A1) teaches a system for modelling task features for continual learning comprising:
a task input gateway arranged to receive a series of task samples (para [0004] “FIGS. 1-4 describe prior art CL models subject to the contemporary problems described herein. FIG. 1 illustrates a CL method 100 according to prior art. In FIG. 1, task 1 and task 2 are received in sequential order as a sequence of new data in step 105.”),
a replay buffer configured to store a subset of previous tasks as a representative of previous tasks that were processed by the system (para [0042] “FIG. 5 illustrates a block diagram of a CL method 500, according to an embodiment. In FIG. 5, past knowledge is stored in a knowledge repository (KR) in step S501. Here, task specific VAEs for previous distinct tasks and classifier heads for all previous tasks are stored in the KR in a knowledge-based function of the method.”),
a task classification engine arranged to perform a task relation process to determine task relations between tasks, wherein the task relations are based at least partly on a subset of previous tasks accessed from the replay buffer (para [0042] “The distribution consistency score is used to estimate a training dataset similarity between the new task and a previous task and the predictor-label association score is used to estimate the test error when using a previous task-specific encoder for classification of a new task. Both of these scores are used in step S506 to determine whether a similar task to the new task is stored in the KR.”).
an output module configured to output the task relations to be used on continual learning, and wherein the replay buffer is updated by storing a subset of the outputs (para [0042] “The distribution consistency score is used to estimate a training dataset similarity between the new task and a previous task and the predictor-label association score is used to estimate the test error when using a previous task-specific encoder for classification of a new task. Both of these scores are used in step S506 to determine whether a similar task to the new task is stored in the KR. If so (“Yes” in step S506), the VAE of the similar task is reused in step S507. If not (“No” in step S506), a new task-specific VAE is trained for the new task in step S508 and the new VAE is stored in the KR.”).
Does not explicitly disclose
a task feature extraction engine arranged to process the received task samples and extract task invariant and task variant features,
However, Ebrahimi (“Adversarial Continual Learning”)
a task feature extraction engine arranged to process the received task samples and extract task invariant and task variant features (pg. 1-2; “In this paper, we propose a novel adversarial continual learning (ACL) method in which a disjoint latent space representation composed of task-specific or private latent space is learned for each task and a task-invariant or shared feature space is learned for all tasks to enhance better knowledge transfer as well as better recall of the previous tasks.”. Task specific (i.e. variant). Task invariant (i.e. invariant). Pg. 5; “In particular, we would like to disentangle the latent space into the information shared across all tasks (zS) and the independent or private information of each task (zP) which are as distinct as possible while their concatenation followed by a task-specific head outputs the desired targets.”),
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 2,
Choi and Ebrahimi teach a system as per claim 1. Ebrahimi further teaches wherein the task classification engine is configured to decouple task invariant features and task variant features based on the task relations (pg. 1-2; “In this paper, we propose a novel adversarial continual learning (ACL) method in which a disjoint latent space representation composed of task-specific or private latent space is learned for each task and a task-invariant or shared feature space is learned for all tasks to enhance better knowledge transfer as well as better recall of the previous tasks.”. Task specific (i.e. variant). Task invariant (i.e. invariant).),
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 3,
Choi and Ebrahimi teach a system as per claim 1. Ebrahimi further teaches wherein the task classification engine is configured to: capture inner task relations based on processing the task invariant and task invariant features (pg. 2; “The intuition behind our method is that tasks in a sequence share a part of the feature representation but also have a part of the feature representation which is task-specific.” Task specific (i.e., inner task).), construct cross task relations based on the subset of previous tasks accessed from the replay buffer (pg. 3, section 2.1; “In this work, we explicitly store raw samples into a very tiny memory used for replay buffer and we differ from prior work by how these stored examples are used by specific parts of our model (discriminator and shared module) to prevent forgetting in the features found to be shared across tasks.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 4,
Choi and Ebrahimi teach a system as per claim 1. Ebrahimi further teaches wherein the task classification engine is configured to decouple task invariant features and task variant features based at least one of the inner task relations and cross task relations (pg. 6, section 3.1; “The main insight to our approach is decoupling the conventional single representation learned for a sequence of tasks into two parts: a part that must not change because it contains task-specific features without which complete performance retrieval is not possible, and a part that is less prone to change as it contains the core structure of all tasks.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 8,
Choi and Ebrahimi teach a system as per claim 1. Ebrahimi further teaches wherein the system further comprises: a task invariant feature extractor configured to extract task invariant features from the received series of task samples, a task variant feature extractor configured to extract task variant features from the received series of task samples (pg. 1-2; “In this paper, we propose a novel adversarial continual learning (ACL) method in which a disjoint latent space representation composed of task-specific or private latent space is learned for each task and a task-invariant or shared feature space is learned for all tasks to enhance better knowledge transfer as well as better recall of the previous tasks.”. Task specific (i.e. variant). Task invariant (i.e. invariant). Pg. 5; “In particular, we would like to disentangle the latent space into the information shared across all tasks (zS) and the independent or private information of each task (zP) which are as distinct as possible while their concatenation followed by a task-specific head outputs the desired targets.”),
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 9,
Choi and Ebrahimi teach a system as per claim 8. Ebrahimi further teaches wherein the task classification engine is configured to: extract task invariant and task variant features by applying at least one or more constraints wherein the constraints comprise: establishing a boundary between the invariant and variant features generating similar task invariant features across tasks establishing distinct boundaries between task variant features from each task or class (pg. 5; “. In particular, we would like to disentangle the latent space into the information shared across all tasks (zS) and the independent or private information of each task (zP) which are as distinct as possible while their concatenation followed by a task-specific head outputs the desired targets. To this end, we introduce a mapping called Shared (SθS : X → zS) and train it to generate features that fool an adversarial discriminator D. Conversely, the adversarial discriminator (DθD : zS → T ) attempts to classify the generated features by their task labels (Tk∈{0,···,T}) .”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 16,
Choi and Ebrahimi teach a system as per claim 1. Ebrahimi further teaches wherein the modelling task features comprise identifying task invariant and task variant features based on the inner task relations and cross task relations, wherein the system provides a model for learning based on resolving tasks into task invariant features and task variant features (pg. 5; “In particular, we would like to disentangle the latent space into the information shared across all tasks (zS) and the independent or private information of each task (zP) which are as distinct as possible while their concatenation followed by a task-specific head outputs the desired targets.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 17,
Choi and Ebrahimi teach a system as per claim 1. Ebrahimi further teaches wherein the system further comprises: a classifier arranged to classify tasks based on a specific class a discriminator arranged to discriminate the differentiate between the task invariant and variant features of each task (pg. 5; “In particular, we would like to disentangle the latent space into the information shared across all tasks (zS) and the independent or private information of each task (zP) which are as distinct as possible while their concatenation followed by a task-specific head outputs the desired targets. To this end, we introduce a mapping called Shared (SθS : X → zS) and train it to generate features that fool an adversarial discriminator D. Conversely, the adversarial discriminator (DθD : zS → T ) attempts to classify the generated features by their task labels (Tk∈{0,···,T}) .”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Claims 5-7 and 10-13 are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Choi/Ebrahimi, as applied above, and further in view of Varshney et al. (US-20240013094-A1).
Regarding Claim 5,
Choi and Ebrahimi teach a system as per claim 2.
Choi and Ebrahimi do not explicitly disclose
wherein the system is configured to determine contrastive learning pairs, wherein the inner task relations and the cross task relations are defined by the determined contrastive learning pairs.
However, Varshney (US 20240013094 A1) teaches
wherein the system is configured to determine contrastive learning pairs, wherein the inner task relations and the cross task relations are defined by the determined contrastive learning pairs (para [0047] “To minimize the likelihood of incorrect (x.sub.jk.sup.i+1, y.sub.j+1.sup.i+1)) pairs, the supervised contrastive fine-tuning of IL.sub.i+1, as shown in FIG. 4C is done.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi and Ebrahimi with the contrastive pair of Varshney.
Doing so would allow for improving the quality of generative replay and overall classification performance (Varshney para [0027]).
Regarding Claim 6,
Choi, Ebrahimi, and Varshney teach a system as per claim 3. Ebrahimi further teaches wherein the task classification engine is configured to determine multiple contrasts to decompose task invariant features and task variant features (pg. 5; “In particular, we would like to disentangle the latent space into the information shared across all tasks (zS) and the independent or private information of each task (zP) which are as distinct as possible while their concatenation followed by a task-specific head outputs the desired targets.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 7,
Choi, Ebrahimi, and Varshney teach a system as per claim as per claim 4. Ebrahimi further teaches wherein the task classification engine is configured to determine three types of contrast to decompose task invariant features and task variant features (pg. 5; “We begin by learning fk θ as a mapping from Xk to Yk. For C-way classification task with a cross-entropy loss,”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 10,
Choi, Ebrahimi, and Varshney teach a system as per claim 6. Ebrahimi further teaches wherein the task classification engine is configured to decouple the task invariant and task variant features based on: determining an orthogonal distance loss function, applying the orthogonal distance loss function to the identified task invariant and task variant features (pg. 5-6; “We further factorize zS and zP by using orthogonality constraints introduced in [30], also known as “difference” loss in the domain adaptation literature [4], to prevent the shared features between all tasks from appearing in the private encoded features.”), determining contrastive learning pairs of features, utilise the learning pairs to further decouple the task invariant and task variant features (pg. 2; “To disentangle the features associated with each task, we propose a novel adversarial learning approach to enforce the shared features to be task-invariant and employ orthogonality constraints [30] to enforce the shared features to not appear in the task-specific space”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 11,
Choi, Ebrahimi, and Varshney teach a system as per claim 10. Ebrahimi further teaches wherein the task classification engine is configured to determine inner task relations, wherein the inner task relations are determined based on the learning pairs that decouple the task invariant and task variant features while clustering the invariant features together regardless of class (pg. 12; “In contrast, in the generated features without a discriminator in the fourth column for task #20, we observe a non-uniformly distributed mixture of features where small clusters can be found for some classes showing an entangled representation within each task.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 12,
Choi, Ebrahimi, and Varshney teach a system as per claim 10. Ebrahimi further teaches wherein the task classification engine is further configured to: apply a classifier to the task variant features wherein the classifier is configured to group task variant features for a particular class together, determine learning pairs of task variant features for each defined class (pg. 5; “Conversely, the adversarial discriminator (DθD : zS → T ) attempts to classify the generated features by their task labels (Tk∈{0,···,T}) . This is achieved when the discriminator is trained to maximize the probability of assigning the correct task label to generated features while simultaneously S is trained to confuse the discriminator by minimizing log(D(S(xk))). This corresponds to the following T-way classification cross-entropy adversarial loss for this minimax game”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Regarding Claim 13,
Choi, Ebrahimi, and Varshney teach a system as per claim 10. Ebrahimi further teaches wherein the task classification engine is configured to: extract a feature of a sample of previous tasks from the replay buffer (pg. 1; “Another stream of approaches in continual learning relies on explicit or implicit experience replay by storing raw samples or training generative models, respectively.”), determine additional updated learning pairs of task variant features, task invariant features and task invariant and variant features based on the feature from the replay buffer, determine a cross task relations based on the updated learning pairs (pg. 5; “In particular, we would like to disentangle the latent space into the information shared across all tasks (zS) and the independent or private information of each task (zP) which are as distinct as possible while their concatenation followed by a task-specific head outputs the desired targets.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify the continual learning model of Choi with the task-specific and task-invariant features of Ebrahimi.
Doing so would allow for enhancing the knowledge transfer between previous tasks (Ebrahimi pg. 1-2;).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HENRY K NGUYEN whose telephone number is (571)272-0217. The examiner can normally be reached Mon - Fri 9:00am-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, Li B Zhen can be reached at 5712723768. 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.
/HENRY NGUYEN/Primary Examiner, Art Unit 2121
