DETAILED ACTION
This action is responsive to the Request for Continued Examination filed on 04/13/2026 for application 17/520,448. Claims 1-31 are pending in the case. Claims 1, 9, 16 and 23 are independent claims. Claims 1-5, 9-11, 13-19 and 21-31 are amended.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 04/13/2026 has been entered.
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 .
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.
Claim Objections
Claim 2 objected to because of the following informalities: Duplicate “the” word in claim 2, …wherein the the first subset and the second subset comprise respective…
Appropriate correction is required.
Claim 24 objected to because of the following informalities: Duplicate “the” word in claim 24, …selecting the the first subset and the second subset based…
Appropriate correction is required.
Claim 26 objected to because of the following informalities: Duplicate “the” word in claim 26, …indicate the the first subset or the second subset based….
Appropriate correction is required.
Claim Rejections - 35 USC § 112
Claim 2 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 2 recites the limitation the respectively different information. There is insufficient antecedent basis for this limitation in the claim.
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 1-31 are rejected under 35 U.S.C. 101 because the claims are directed to an abstract idea or mental process.
Regarding claim 1:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites calculate a first task descriptor which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites to infer first information for the first input which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass using judgement to predict sets of information. See 2106.04.(a)(2).III.C.
The claim recites calculate a second task descriptor which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites to infer second information for the second input which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass using judgement to predict sets of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
Processor (merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
one or more circuits (merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
selectively activate, based, at least in part, on the calculated first task descriptor, a first subset of neural network nodes of the architecture of the neural network to(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
based, at least in part, on network specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
based, at least in part, on a second input to the neural network specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
selectively activate, based, at least in part, on the calculated second task descriptor, a second subset of neural network nodes of the architecture of the neural network to(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
wherein at least one neural network node of the architecture is not shared between the first and second subsets specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) (b) (c) (f) and (g) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
Additional elements (d) (e) and (h) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) - (h) in the claim do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 2:
The rejection of claim 1 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites infer the respectively different information based, at least in part, on one or more features of respective input data which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information that is derived from a separate set of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
the first subset and the second subset comprise respective different sets of neurons of the neural network(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
to be input into the neural network(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) and (b) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) and (b) in claim 2 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 3:
The rejection of claim 1 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites to infer the respectively different information which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information. See 2106.04.(a)(2).III.C.
The claim recites compute one or more data values … the one or more data values indicating a state of the one or more convolutional layers which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
wherein the neural network is a neural coding network comprising one or more convolutional layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
, at least in part, on respectively different information inferred for different tasks, (merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) and (b) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) and (b) in claim 3 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 4:
The rejection of claim 1 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites wherein the first information computed… is based, at least in part, on a first set of image data… and the second information computed… is based, at least in part, on a second set of image data which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information derived from separate images. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
by the neural network(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
input to the neural network specifies linking the use of a judicial exception to a particular technological environment or field of use(see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional element (a) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
Additional elements (b) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely links the use of a judicial exception to a particular technological environment or field of use(see MPEP 2106.05(h)).
The additional element(s) (a) and (b) in claim 4 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 5:
The rejection of claim 1 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites computing at least a set of state data, a set of error data, and a set of corrected state data to be used to infer different information for different tasks which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
neural network comprises one or more neural coding blocks(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
using different portions of the neural network(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
Additional element (b) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
The additional element(s) (a) and (b) in claim 5 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 6:
The rejection of claim 1 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites compute a set of data comprising a respective task descriptor to indicate a respective different portions of the neural network which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
neural network comprises one or more layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional element (a) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 6 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 7:
The rejection of claim 1 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites of one or more computational operations…to generate state data for the one or more layers which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
the neural network comprises at least one block …to be performed on one or more layers of the neural network(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional element (a) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 7 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 8:
The rejection of claim 1 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim does not contain elements that would warrant a Step 2A Prong 1 analysis.
Subject Matter Eligibility Analysis Step 2A Prong 2:
The claim recites wherein the neural network comprises one or more convolutional layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional element (a) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 8 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 9:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites calculate a first task descriptor which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites to infer first information for the first input which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass using judgement to predict sets of information. See 2106.04.(a)(2).III.C.
The claim recites calculate a second task descriptor which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites to infer second information for the second input which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass using judgement to predict sets of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
comprising non-transitory memory to store instructions that(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
as a result of execution by one or more processors (merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
selectively activate, based, at least in part, on the calculated first task descriptor, a first subset of neural network nodes of the architecture of the neural network to(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
based, at least in part, on network specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
based, at least in part, on a second input to the neural network specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
selectively activate, based, at least in part, on the calculated second task descriptor, a second subset of neural network nodes of the architecture of the neural network to(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
wherein at least one neural network node of the architecture is not shared between the first and second subsets specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) (b) (c) (f) and (g) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
Additional elements (d) (e) and (h) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) – (h) in the claim do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 10:
The rejection of claim 9 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites infer the respectively different information based on a first set of input image data and a second set of input image data, the first set of input image data comprising the first input and the second set of input image data comprising the second input which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information that is derived from a separate set of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2B:
The claim does not include any additional element, when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 11:
The rejection of claim 9 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites computing at least a set of data representing a predicted state of the neural coding block for each input to the neural coding block which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites the predicted state to be used to infer respectively different information which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information based on a calculation. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
neural network comprises one or more neural coding blocks(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional element (a) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 11 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 12:
The rejection of claim 9 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites compute a set of data comprising a respective task descriptor to indicate a respective different portion based of the neural network which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
neural network comprises one or more layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional element(s) (a) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 12 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 13:
The rejection of claim 9 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites one or more blocks of computational operations… based, at least on part, on a predicted state computed which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites and an error representing the difference between the predicted state and a correct state for respectively different information which is an abstract idea (Mathematical Relationships (see MPEP 2106.04(a)(2)(I)(A)))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
to correct one or more states of the neural network(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
by the neural network(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
Subject Matter Eligibility Analysis Step 2B:
Additional element(s) (a) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
Additional element(s) (b) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
The additional element(s) (a) and (b) in claim 13 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 14:
The rejection of claim 9 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites infer a first output…based, at least in part, on the first input to the neural network, and a second output…based, at least in part, on the second input to the neural network which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting an outputs based on inputs. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
using a first portion of the neural network … using a second portion of the neural network(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
Subject Matter Eligibility Analysis Step 2B:
Additional element (a) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
The additional element(s) (a) in claim 14 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 15:
The rejection of claim 9 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites infer respectively different information, the respectively different information comprising one or more features of image data input to the neural network which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information from an image. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
wherein the neural network is a neural coding network comprising one or more convolutional layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional element (a) does not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 15 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 16:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites calculate a first task descriptor which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites to infer first information for the first input which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass using judgement to predict sets of information. See 2106.04.(a)(2).III.C.
The claim recites calculate a second task descriptor which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites to infer second information for the second input which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass using judgement to predict sets of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
non-transitory machine-readable medium having stored thereon one or more instructions (merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
which if performed by one or more processors, cause the one or more processors to at least (merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
selectively activate, based, at least in part, on the calculated first task descriptor, a first subset of neural network nodes of the architecture of the neural network to(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
based, at least in part, on network specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
based, at least in part, on a second input to the neural network specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
selectively activate, based, at least in part, on the calculated second task descriptor, a second subset of neural network nodes of the architecture of the neural network to(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
wherein at least one neural network node of the architecture is not shared between the first and second subsets specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) (b) (c) (f) and (g) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
Additional elements (d) (e) and (h) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) – (h) in the claim do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 17:
The rejection of claim 16 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites select respectively different sets of neurons of the neural network which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user choosing a portion of the neural network to operate. See 2106.04.(a)(2).III.C.
The claim recites infer respectively different information based, at least in part, on one or more features of input data to be input into the neural network which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information from a set of data. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2B:
The claim does not include any additional element, when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 18:
The rejection of claim 16 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites compute a set of data comprising information to indicate one or more neurons of the neural network which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites to infer respectively different information for different tasks which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2B:
The claim does not include any additional element, when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 19:
The rejection of claim 16 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites to compute a set of data comprising information to indicate the first subset or the second subset based, at least in part, on a difference between the first input and the second input which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
wherein the neural network comprises one or more layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 19 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 20:
The rejection of claim 16 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites one or more computational operations to be performed …to generate state data… which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
...to be performed on one or more layers of the neural network…(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
…for the one or more layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) and (b) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) and (b) in claim 20 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 21:
The rejection of claim 16 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites compute a set of data representing a predicted state for each layer of one or more neural coding blocks of the neural network which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites the predicted state usable to infer respectively different information which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting a set of information based on a calculation. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
further comprising instructions that, if performed by the one or more processors, cause the one or more processors(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
Subject Matter Eligibility Analysis Step 2B:
Additional element(s) (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
The additional element(s) (a) in claim 21 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 22:
The rejection of claim 16 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim does not contain elements that would warrant a Step 2A Prong 1 analysis.
Subject Matter Eligibility Analysis Step 2A Prong 2:
wherein the first input comprises a first type of image information inferred by the neural network using a first portion of the neural network…and the second input comprises a second type of information inferred by the neural network using a second portion of the neural network(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 22 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 23:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites calculate a first task descriptor which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites to infer first information for the first input which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass using judgement to predict sets of information. See 2106.04.(a)(2).III.C.
The claim recites calculate a second task descriptor which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites to infer second information for the second input which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass using judgement to predict sets of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
selectively activate, based, at least in part, on the calculated first task descriptor, a first subset of neural network nodes of the architecture of the neural network to(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
based, at least in part, on network specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
based, at least in part, on a second input to the neural network specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
selectively activate, based, at least in part, on the calculated second task descriptor, a second subset of neural network nodes of the architecture of the neural network to(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
wherein at least one neural network node of the architecture is not shared between the first and second subsets specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) (d) and (e) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
Additional elements (b) (c) and (f) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) – (f) in the claim do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 24:
The rejection of claim 23 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites selecting the first subset and the second subset which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user choosing a portion of the neural network to operate based on sets of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
the first subset and the second subset comprising different respective sets of neurons to infer respectively different information(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
based, at least in part, on one or more features of input data to be input into the neural network specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h))
Subject Matter Eligibility Analysis Step 2B:
Additional element(s) (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
Additional elements (b) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) and (b) in claim 24 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 25:
The rejection of claim 23 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites compute state data based on one or more inputs to the neural network, the state data usable to infer respectively different information which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
the neural network comprises one or more neural coding blocks comprising one or more convolutional layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 25 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 26:
The rejection of claim 23 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites compute a set of data comprising information to indicate the first subset or the second subset based, at least in part, on the first task descriptor or the second task descriptor which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
Subject Matter Eligibility Analysis Step 2A Prong 2:
one or more layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 26 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 27:
The rejection of claim 23 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites wherein the first information inferred … and the second information is inferred which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
by the neural network is inferred using a first set of neurons of the neural network… by the neural network using a second set of neurons of the neural network different from the first set(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
Subject Matter Eligibility Analysis Step 2B:
Additional element(s) (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
The additional element(s) (a) in claim 27 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 28:
The rejection of claim 23 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites calculating a set of data values to indicate different subsets of the neural network based, at least in part, on input data to the neural network which is an abstract idea (Mathematical Calculations (see MPEP 2106.04(a)(2)(I)(C))).
The claim recites infer the respectively different information based, at least in part, on the input data which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information that is derived from a separate set of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
the one or more different subsets comprising one or more neurons of one or more layers of the neural network to be used to (merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 28 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 29:
The rejection of claim 23 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites inferring a first output comprising the first information based, at least in part, on the first input comprising a first type of information and inferring a second output comprising the second information based, at least in part, on the second input comprising a second type of information which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information derived from separate sets of information. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2B:
The claim does not include any additional element, when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 30:
The rejection of claim 23 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim recites infer respectively different information, the respectively different information comprising one or more features of image data input to the neural network which, under the broadest reasonable interpretation, covers performance of the limitation in the mind with or without a physical aid. The limitations encompass a user predicting sets of information from an image. See 2106.04.(a)(2).III.C.
Subject Matter Eligibility Analysis Step 2A Prong 2:
wherein the neural network is a neural coding network comprising one or more convolutional layers(merely specifies a particular technological environment in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)))
Subject Matter Eligibility Analysis Step 2B:
Additional elements (a) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation merely specifies a field of use in which the abstract idea is to take place, i.e. a field of use (see MPEP 2106.05(h)).
The additional element(s) (a) in claim 30 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Regarding claim 31:
The rejection of claim 23 is incorporated and further claim recites further additional elements/limitations:
Subject Matter Eligibility Analysis Step 2A Prong 1:
The claim does not contain elements that would warrant a Step 2A Prong 2 analysis.
Subject Matter Eligibility Analysis Step 2A Prong 2:
training a first portion of the neural network based, at least in part, on a first set of data…training a second portion of the neural network based, at least in part, on a second set of data; (merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
the first set of data comprises a first type of information and the second set of data comprises a second type of information(merely recites a generic computer on which to perform the abstract idea, e.g. "apply it on a computer" (see MPEP 2106.05(f)))
Subject Matter Eligibility Analysis Step 2B:
Additional element(s) (a) and (b) do not integrate the abstract idea into a practical application nor do the additional limitation provide significantly more than the abstract idea because the limitation amount to no more than mere instructions to apply the exception using a generic computer component. Please see MPEP §2106.05(f).
The additional element(s) (a) (b) in claim 31 do/does not include any additional elements , when considered separately and in combination, that amount to an integration of the judicial exception into a practical application, nor significantly more than the judicial exception for the reasons set forth in step 2A prong 2 analysis above. The claim is not patent eligible.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(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.
Claim(s) 1-31 is/are rejected under 35 U.S.C. 102 (a)(1) by Abdulnabi et al(Multi-Task CNN Model for Attribute Prediction), henceforth known as Abdulnabi.
Regarding claim 1:
Abdulnabi teaches a processor comprising: one or more circuits to(Abdulnabi, Page 1950, Paragraph 4,“The first approach is more or less applicable depending on the available resources (CPU/GPU and Memory)”)
Abdulnabi teaches calculate a first task descriptor based, at least in part, on a first input to a neural network implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers(Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute.” where CNN-1 predicting binary Attribute 1 using the input image in Figure 2 corresponds to calculate a first task descriptor based, at least in part, on a first input to a neural network implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers as CNN-1 predicting a binary Attribute 1 corresponds to a first task descriptor with the input to CNN-1 being considered a first input and CNN-1 shows a plurality of neural network nodes arranged in a series of connected layers Conv1 to Conv 5)
Abdulnabi teaches selectively activate, based, at least in part, on the calculated first task descriptor, a first subset of neural network nodes of the architecture of the neural network to infer first information for the first input(Abdulnabi, Page 1952, Figure 2, “…Each CNN will predict one binary attribute” where the CNN-1 corresponds to a first subset of neurons being used to predict a first information of Attribute 1 to form a task-specific classifier corresponds to selectively activating a first subset of neural network nodes of the architecture of the neural network to infer first information for the first input.
Abdulnabi teaches calculate a second task descriptor based, at least in part, on a second input to the neural network(Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute.” where CNN-M predicting binary Attribute M using the input image in Figure 2 corresponds to calculate a second task descriptor based, at least in part, on a second input to the neural network as CNN-M predicting a binary Attribute M corresponds to a second task descriptor with the input to CNN-M being considered a second input)
Abdulnabi teaches selectively activate, based, at least in part, on the calculated second task descriptor, a second subset of neural network nodes of the architecture of the neural network to infer second information for the second input, wherein at least one neural network node of the architecture is not shared between the first and second subsets(Abdulnabi, Page 1952, Figure 2, “…Each CNN will predict one binary attribute” where the CNN-M corresponds to a second subset of neurons being used to predict a second information of Attribute M to form a task-specific classifier corresponds to selectively activating a second subset of neural network nodes of the architecture of the neural network to infer second information for the second input, wherein at least one neural network node of the architecture is not shared between the first and second subsets as predicting Attribute M uses CNN-M with shared L latent space as part of the CNN-based architecture and without using the other CNN instances, such as CNN-1)
Regarding claim 2:
Abdulnabi teaches the processor of claim 1(and thus the rejection of claim 1 is incorporated)
Abdulnabi teaches wherein the first subset and the second subset comprise respective different sets of neurons of the neural network to infer the respectively different information based, at least in part, on one or more features of respective input data to be input into the neural network(Abdulnabi, Page 1952, Figure 2, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute”, where CNN-1 and CNN-M are considered a different set of neurons of the neural network that are being used to infer different information based, at least in part, on one or more features of respective input data to be input into the neural network as each CNN is used to predict a different binary attribute from the input image and the model as a whole comprises multiple CNN’s.
Regarding claim 3:
Abdulnabi teaches the processor of claim 1(and thus the rejection of claim 1 is incorporated)
Abdulnabi teaches wherein the neural network is a neural coding network comprising one or more convolutional layers to compute one or more data values based, at least in part, on respectively different information inferred for different tasks, the one or more data values indicating a state of the one or more convolutional layers where the state is to be used to infer the respectively different information(Abdulnabi, Page 1952, Figure 2, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where the information CNN-1 to CNN-M are considered CNN’s with convolutional layers that compute one or more data values based on the predicting binary attributes (respectively different tasks with different information using different CNN’s) and the use those values with Shared L to predict the attributes is considered indicating a state that is used to infer respectively different information)
Regarding claim 4:
Abdulnabi teaches the processor of claim 1(and thus the rejection of claim 1 is incorporated)
Abdulnabi teaches wherein the first information computed by the neural network is based, at least in part, on a first set of image data input to the neural network, and the second information computed by the neural network is based, at least in part, on a second set of image data input to the neural network(Abdulnabi, Page 1952, Figure 2, where every input to each CNN network is considered a different input and the image input to CNN-1 corresponds to a first set of image data input to compute the first information of Attribute 1 and the image input to CNN-M corresponds to a second set of image data input to compute the second information of Attribute M)
Regarding claim 5:
Abdulnabi teaches the processor of claim 1(and thus the rejection of claim 1 is incorporated)
Abdulnabi teaches wherein the neural network comprises one or more neural coding blocks, each neural coding block computing at least a set of state data(Abdulnabi, Page 1955, “During a training epoch, the forward pass will generate the input for the multi-task loss layer from all the CNN models” where the feature maps and weights that CNN’s inherently have are considered a set of state data and a forward pass is considered computing), a set of error data(Abdulnabi, Page 1955, “During a training epoch, the forward pass will generate the input for the multi-task loss layer from all the CNN models” where the loss layer is considered a set of error data as it contains an error/loss function), and a set of corrected state data to be used to infer different information for different tasks(Abdulnabi, Page 1955, “After optimizing (2) using the proposed algorithm III-D, the output is the overall model weight matrix , where each column in will be dedicated to its specific corresponding CNN model and is taken back in the backward pass alongside the gradients with respect to its input” where the updated weights during training makes the neural network better at predicting which is considered a more corrected state data to be used to infer respectively different tasks with different information using different CNN’s) using different portions of the neural network(Abdulnabi, Page 1954, Col. 2, Paragraph 4, “Recall, that during the training procedure of M CNN models, each of them is responsible for predicting a single attribute. attribute” where each model being responsible for predicting a single attribute corresponds to a different portion of the neural network inferring a different tasks)
Regarding claim 6:
Abdulnabi teaches the processor of claim 1(and thus the rejection of claim 1 is incorporated)
Abdulnabi teaches wherein the neural network comprises one or more layers(Abdulnabi, Page 1952, Figure 2, where figure 2 shows multiple layers with Conv1-Conv5 that computer the input image (a set of data) uses a neural network (one or more portions) to infer binary attribute(a respective different information)) to compute a set of data comprising a respective task descriptor to indicate a respective different portions based of the neural network(Abdulnabi, Page 1955, “After optimizing (2) using the proposed algorithm III-D, the output is the overall model weight matrix , where each column in will be dedicated to its specific corresponding CNN model and is taken back in the backward pass alongside the gradients with respect to its input” where the updated weights during training makes the neural network better at predicting which is considered a more corrected state data to be used to infer respective information(binary attributes) using different CNN’s)
Regarding claim 7:
Abdulnabi teaches the processor of claim 1(and thus the rejection of claim 1 is incorporated)
Abdulnabi teaches wherein the neural network comprises at least one block of one or more computational operations to be performed on one or more layers of the neural network to generate state data for the one or more layers(Abdulnabi, Page 1955, “During a training epoch, the forward pass will generate the input for the multi-task loss layer from all the CNN models” where training using forward pass and loss layer are considered computations operations that are performed on layers of a neural network that generates the state data of layers of the CNN after the forward pass is completed (See Abdulnabi, Page 1952, Col. 2, Paragraph 1, “After the forward pass in all of the CNN models…the joint loss layer and sharing the visual knowledge, each CNN model will take back its specific parameters through backpropagation in the backward pass” )
Regarding claim 8:
Abdulnabi teaches the processor of claim 1(and thus the rejection of claim 1 is incorporated)
Abdulnabi teaches wherein the neural network comprises one or more convolutional layers.(Abdulnabi, Page 1952, Figure 2, where figure 2 shows convolutional layers Conv1-Conv5)
Regarding claim 9:
Abdulnabi teaches a system, comprising non-transitory memory to store instructions that, as a result of execution by one or more processors cause the system to (Abdulnabi, Page 1950, Paragraph 4,“The first approach is more or less applicable depending on the available resources (CPU/GPU and Memory)”)
Abdulnabi teaches calculate a first task descriptor based, at least in part, on a first input to a neural network implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers(Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute.” where CNN-1 predicting binary Attribute 1 using the input image in Figure 2 corresponds to calculate a first task descriptor based, at least in part, on a first input to a neural network implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers as CNN-1 predicting a binary Attribute 1 corresponds to a first task descriptor with the input to CNN-1 being considered a first input and CNN-1 shows a plurality of neural network nodes arranged in a series of connected layers Conv1 to Conv 5)
Abdulnabi teaches selectively activate, based, at least in part, on the calculated first task descriptor, a first subset of neural network nodes of the architecture of the neural network to infer first information for the first input(Abdulnabi, Page 1952, Figure 2, “…Each CNN will predict one binary attribute” where the CNN-1 corresponds to a first subset of neurons being used to predict a first information of Attribute 1 to form a task-specific classifier corresponds to selectively activating a first subset of neural network nodes of the architecture of the neural network to infer first information for the first input.
Abdulnabi teaches calculate a second task descriptor based, at least in part, on a second input to the neural network(Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute.” where CNN-M predicting binary Attribute M using the input image in Figure 2 corresponds to calculate a second task descriptor based, at least in part, on a second input to the neural network as CNN-M predicting a binary Attribute M corresponds to a second task descriptor with the input to CNN-M being considered a second input)
Abdulnabi teaches selectively activate based, at least in part, on the calculated second task descriptor, a second subset of neural network nodes of the architecture of the neural network to infer second information for the second input, wherein at least one neural network node of the architecture is not shared between the first and second subsets(Abdulnabi, Page 1952, Figure 2, “…Each CNN will predict one binary attribute” where the CNN-M corresponds to a second subset of neurons being used to predict a second information of Attribute M to form a task-specific classifier corresponds to selectively activating a second subset of neural network nodes of the architecture of the neural network to infer second information for the second input, wherein at least one neural network node of the architecture is not shared between the first and second subsets as predicting Attribute M uses CNN-M with shared L latent space as part of the CNN-based architecture and without using the other CNN instances, such as CNN-1)
Regarding claim 10:
Abdulnabi teaches the system of claim 9(and thus the rejection of claim 9 is incorporated)
Abdulnabi teaches wherein the neural network is to infer respectively different information based on a first set of input image data and a second set of input image data, the first set of input image data comprising the first input and the second set of input image data comprising the second input(Abdulnabi, Page 1952, Figure 2, where every input to each CNN network is considered a different input and the image input to CNN-1 corresponds to a first set of image data input to compute the first information of Attribute 1 and the image input to CNN-M corresponds to a second set of image data input to compute the second information of Attribute M)
Regarding claim 11:
Abdulnabi teaches the system of claim 9(and thus the rejection of claim 9 is incorporated)
Abdulnabi teaches wherein the neural network comprises one or more neural coding blocks, each neural coding block computing at least a set of data representing a predicted state of the neural coding block for each input to the neural coding block(Abdulnabi, Page 1955, “During a training epoch, the forward pass will generate the input for the multi-task loss layer from all the CNN models” where the training of the CNN and updating weights during back-propagation is considered computing a set of data representing a predicted state of the neural network coding block based on an input), the predicted state to be used to infer respectively different information(Abdulnabi, Page 1955, “After optimizing (2) using the proposed algorithm III-D, the output is the overall model weight matrix , where each column in will be dedicated to its specific corresponding CNN model and is taken back in the backward pass alongside the gradients with respect to its input” where the updated weights during training makes each CNN model neural network better at predicting each desperate attribute is considered a predicted state data to be used to infer(i.e. predict) respective information(binary attributes))
Regarding claim 12:
Abdulnabi teaches the system of claim 9(and thus the rejection of claim 9 is incorporated)
Abdulnabi teaches wherein the neural network comprises one or more layers(Abdulnabi, Page 1952, Figure 2, where figure 2 shows multiple layers with Conv1-Conv5 that computer the input image (a set of data) uses a neural network (one or more portions) to infer binary attribute(a respective different information)) to compute a set of data comprising a respective task descriptor to indicate a respective different portions based of the neural network(Abdulnabi, Page 1955, “After optimizing (2) using the proposed algorithm III-D, the output is the overall model weight matrix , where each column in will be dedicated to its specific corresponding CNN model and is taken back in the backward pass alongside the gradients with respect to its input” where the updated weights during training makes the neural network better at predicting which is considered a more corrected state data to be used to infer respective information(binary attributes))
Regarding claim 13:
Abdulnabi teaches the system of claim 9(and thus the rejection of claim 9 is incorporated)
Abdulnabi teaches wherein the neural network comprises one or more blocks of computational operations to correct one or more states of the neural network(Abdulnabi, Page 1955, “After optimizing (2) using the proposed algorithm III-D, the output is the overall model weight matrix , where each column in will be dedicated to its specific corresponding CNN model and is taken back in the backward pass alongside the gradients with respect to its input” where the updated weights during training makes the neural network better at predicting which is considered a more corrected state data to be used to infer respective information(binary attributes) based, at least on part, on a predicted state computed by the neural network(Abdulnabi, Page 1955, “During a training epoch, the forward pass will generate the input for the multi-task loss layer from all the CNN models” TODO) and an error (Abdulnabi, Page 1955, “During a training epoch, the forward pass will generate the input for the multi-task loss layer from all the CNN models” where the loss layer is considered a set of error data as it contains an error/loss function) representing the difference between the predicted state and a correct state for respectively different information (Abdulnabi, Page 1954, Col. 1, Equation 2, where the predicted state refers to the model’s predicted output and the correct state refers to the actual label for the attribute and objective function compares the correct state, Yim , to the predicted output, (Lsm )TXim , for attributes m and i being the training sample, by penalizing the model if the predicted outcome is on the wrong side of the margin of correct/confidence)
Regarding claim 14:
Abdulnabi teaches the system of claim 9(and thus the rejection of claim 9 is incorporated)
Abdulnabi teaches wherein the neural network is to infer a first output using a first portion of the neural network based, at least in part, on the first input to the neural network, and the second output using a second portion of the neural network based, at least in part, on a second input to the neural network (Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where CNN-1 and CNN-M are considered a first and second portion of a neural network and output a respective first and second output(binary attributes 1 and M) with the input to CNN-1 being considered a first input and the input to CNN-M being considered a second input)
Regarding claim 15:
Abdulnabi teaches the system of claim 9(and thus the rejection of claim 9 is incorporated)
Abdulnabi teaches wherein the neural network is a neural coding network comprising one or more convolutional layers to infer the respectively different information(Abdulnabi, Page 1952, Figure 2, where figure 2 shows convolutional layers Conv1-Conv5), the respectively different information comprising one or more features of image data input to the neural network (Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where the model predicting a binary attribute of the input image is considered inferring one or more feature of the input image)
Regarding claim 16:
Abdulnabi teaches a non-transitory machine-readable medium having stored thereon one or more instructions, which if performed by one or more processors to at least: (Abdulnabi, Page 1950, Paragraph 4,“The first approach is more or less applicable depending on the available resources (CPU/GPU and Memory)”)
Abdulnabi teaches calculate a first task descriptor based, at least in part, on a first input to a neural network implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers(Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute.” where CNN-1 predicting binary Attribute 1 using the input image in Figure 2 corresponds to calculate a first task descriptor based, at least in part, on a first input to a neural network implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers as CNN-1 predicting a binary Attribute 1 corresponds to a first task descriptor with the input to CNN-1 being considered a first input and CNN-1 shows a plurality of neural network nodes arranged in a series of connected layers Conv1 to Conv 5)
Abdulnabi teaches selectively activate, based, at least in part, on the calculated first task descriptor, a first subset of neural network nodes of the architecture of the neural network to infer first information for the first input(Abdulnabi, Page 1952, Figure 2, “…Each CNN will predict one binary attribute” where the CNN-1 corresponds to a first subset of neurons being used to predict a first information of Attribute 1 to form a task-specific classifier corresponds to selectively activating a first subset of neural network nodes of the architecture of the neural network to infer first information for the first input.
Abdulnabi teaches calculate a second task descriptor based, at least in part, on a second input to the neural network(Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute.” where CNN-M predicting binary Attribute M using the input image in Figure 2 corresponds to calculate a second task descriptor based, at least in part, on a second input to the neural network as CNN-M predicting a binary Attribute M corresponds to a second task descriptor with the input to CNN-M being considered a second input)
Abdulnabi teaches selectively activate, based, at least in part, on the calculated second task descriptor, a second subset of neural network nodes of the architecture of the neural network to infer second information for the second input, wherein at least one neural network node of the architecture is not shared between the first and second subsets(Abdulnabi, Page 1952, Figure 2, “…Each CNN will predict one binary attribute” where the CNN-M corresponds to a second subset of neurons being used to predict a second information of Attribute M to form a task-specific classifier corresponds to selectively activating a second subset of neural network nodes of the architecture of the neural network to infer second information for the second input, wherein at least one neural network node of the architecture is not shared between the first and second subsets as predicting Attribute M uses CNN-M with shared L latent space as part of the CNN-based architecture and without using the other CNN instances, such as CNN-1)
Regarding claim 17:
Abdulnabi teaches the machine-readable medium of claim 16(and thus the rejection of claim 16 is incorporated)
Abdulnabi teaches further comprising instructions that, if performed by the one or more processors, cause the one or more processors to select respectively different sets of neurons of the neural network to infer respectively different information based, at least in part, on one or more features of input data to be input into the neural network(Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where using the model is considered selecting neurons for information to be inferred that is based on the image/data that is input into the neural network which is considered inferring respectively different information based on input data that is input into the neural network and where the model predicting a binary attribute of the input image/data is considered inferring one or more feature of the input image/data)
Regarding claim 18:
Abdulnabi teaches the machine-readable medium of claim 16(and thus the rejection of claim 16 is incorporated)
Abdulnabi teaches further comprising instructions that, if performed by the one or more processors, cause the one or more processors to compute a set of data comprising information to indicate one or more neurons of the neural network to infer respectively different information(Abdulnabi, Page 1955, “During a training epoch, the forward pass will generate the input for the multi-task loss layer from all the CNN models” where a forward pass is considered computing a set of data with one or more neurons and the output of a forward pass is considered producing inferred information) for different tasks(Abdulnabi, Page 1954, Col. 2, Paragraph 4, “Recall, that during the training procedure of M CNN models, each of them is responsible for predicting a single attribute. attribute” where each model being responsible for predicting a single attribute corresponds to a different portion of the neural network inferring a different tasks)
Regarding claim 19:
Abdulnabi teaches the machine-readable medium of claim 16(and thus the rejection of claim 16 is incorporated)
Abdulnabi teaches wherein the neural network comprises one or more layers to compute a set of data comprises one or more layer to compute a set of data comprising information to indicate the first subset or the second subset based, at least in part, on a difference between the first input and the second input( Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute.” where CNN-1 and CNN-M computing a different binary attributes(Attribute 1 and Attribute M) based on the input to CNN-1 and the input to CNN-M corresponds the neural network comprises one or more layers to compute a set of data comprises one or more layer to compute a set of data comprising information to indicate the first subset or the second subset based, at least in part, on a difference between the first input and the second as each CNN has layers computing a different binary attribute based on differing and independent inputs)
Regarding claim 20:
Abdulnabi teaches the machine-readable medium of claim 16(and thus the rejection of claim 16 is incorporated)
Abdulnabi teaches wherein the neural network comprises at least one block of one or more computational operations to be performed on one or more layers of the neural network to generate state data for the one or more layers(Abdulnabi, Page 1955, “During a training epoch, the forward pass will generate the input for the multi-task loss layer from all the CNN models” where training using forward pass and loss layer are considered computations operations that are performed on layers of a neural network that generates the state data of layers of the CNN after the forward pass is completed (See Abdulnabi, Page 1952, Col. 2, Paragraph 1, “After the forward pass in all of the CNN models…the joint loss layer and sharing the visual knowledge, each CNN model will take back its specific parameters through backpropagation in the backward pass” )
Regarding claim 21:
Abdulnabi teaches the machine-readable medium of claim 16(and thus the rejection of claim 16 is incorporated)
Abdulnabi teaches further comprising instructions that, if performed by the one or more processors, cause the one or more processors to compute a set of data representing a predicted state for each layer of one or more neural coding blocks of the neural network(Abdulnabi, Page 1955, “During a training epoch, the forward pass will generate the input for the multi-task loss layer from all the CNN models” where the training of the CNN and updating weights during back-propagation is considered computing a set of data representing a predicted state of the neural network coding block based on an input), the predicted state usable to infer respectively different information. (Abdulnabi, Page 1955, “After optimizing (2) using the proposed algorithm III-D, the output is the overall model weight matrix , where each column in will be dedicated to its specific corresponding CNN model and is taken back in the backward pass alongside the gradients with respect to its input” where the updated weights during training makes the neural network better at predicting which is considered a predicted state data to be used to infer(i.e. predict) respective information(binary attributes))
Regarding claim 22:
Abdulnabi teaches the machine-readable medium of claim 16(and thus the rejection of claim 16 is incorporated)
Abdulnabi teaches wherein the first input comprises a first type of image information inferred by the neural network using a first portion of the neural network(Abdulnabi, Page 1952, Figure 2 description, where CNN-1 is considered a first portion of a neural network which infers image information of Attribute 1 with the input into CNN-1) and the second input comprises second type of information inferred by the neural network using a second portion of the neural network(Abdulnabi, Page 1952, Figure 2 description, where CNN-M is considered a second portion of a neural network which infers image information of Attribute M with the input into CNN-M)
Regarding claim 23:
Abdulnabi teaches a method comprising: calculate a first task descriptor based, at least in part, on a first input to a neural network implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers(Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute.” where CNN-1 predicting binary Attribute 1 using the input image in Figure 2 corresponds to calculate a first task descriptor based, at least in part, on a first input to a neural network implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers as CNN-1 predicting a binary Attribute 1 corresponds to a first task descriptor with the input to CNN-1 being considered a first input and CNN-1 shows a plurality of neural network nodes arranged in a series of connected layers Conv1 to Conv 5)
Abdulnabi teaches selectively activate, based, at least in part, on the calculated first task descriptor, a first subset of neural network nodes of the architecture of the neural network to infer first information for the first input(Abdulnabi, Page 1952, Figure 2, “…Each CNN will predict one binary attribute” where the CNN-1 corresponds to a first subset of neurons being used to predict a first information of Attribute 1 to form a task-specific classifier corresponds to selectively activating a first subset of neural network nodes of the architecture of the neural network to infer first information for the first input.
Abdulnabi teaches calculate a second task descriptor based, at least in part, on a second input to the neural network(Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute.” where CNN-M predicting binary Attribute M using the input image in Figure 2 corresponds to calculate a second task descriptor based, at least in part, on a second input to the neural network as CNN-M predicting a binary Attribute M corresponds to a second task descriptor with the input to CNN-M being considered a second input)
Abdulnabi teaches selectively activate, based, at least in part, on the calculated second task descriptor, a second subset of neural network nodes of the architecture of the neural network to infer second information for the second input, wherein at least one neural network node of the architecture is not shared between the first and second subsets(Abdulnabi, Page 1952, Figure 2, “…Each CNN will predict one binary attribute” where the CNN-M corresponds to a second subset of neurons being used to predict a second information of Attribute M to form a task-specific classifier corresponds to selectively activating a second subset of neural network nodes of the architecture of the neural network to infer second information for the second input, wherein at least one neural network node of the architecture is not shared between the first and second subsets as predicting Attribute M uses CNN-M with shared L latent space as part of the CNN-based architecture and without using the other CNN instances, such as CNN-1)
Regarding claim 24:
Abdulnabi teaches the method of claim 23(and thus the rejection of claim 23 is incorporated)
Abdulnabi teaches further comprising selecting the first subset and the second subset based, at least in part, on one or more features of input data to be input into the neural network(Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where using the model is considered selecting neurons for information to be inferred that is based on the image/data that is input into the neural network and where the model predicting a binary attribute of the input image/data is considered inferring one or more feature of the input image/data), the first subset and the second subset comprising different respective sets of neurons(to infer respectively different information(Abdulnabi, Page 1952, Figure 2 and Abdulnabi, Page 1954, Col. 2, Paragraph 4, “Recall, that during the training procedure of M CNN models, each of them is responsible for predicting a single attribute. attribute” where each model being responsible for predicting a single attribute corresponds to a different portion of the neural network inferring a different tasks as Figure 2 shows CNN-1 and CNN-M corresponds to different sets of neurons that are inferring different information (Attribute 1 and Attribute M))
Regarding claim 25:
Abdulnabi teaches the method of claim 23(and thus the rejection of claim 23 is incorporated)
Abdulnabi teaches wherein the neural network comprises one or more neural coding blocks comprising one or more convolutional layers to compute state data based on one or more inputs to the neural network(Abdulnabi, Page 1952, Figure 2, where figure 2 shows convolutional layers Conv1-Conv5), the state data usable to infer respectively different information(Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where the information CNN-1 to CNN-M are considered CNN’s with convolutional layers that compute one or more values based on predicting binary attributes (respectively different information) and the use those values with Shared L to predict attributes is considered a state data that is used to infer respectively different information)
Regarding claim 26:
Abdulnabi teaches the method of claim 23(and thus the rejection of claim 23 is incorporated)
Abdulnabi teaches further comprising one or more layers to compute a set of data comprising information to indicate the first subset or the second subset based, at least in part, on the first task descriptor or the second task descriptor(Abdulnabi, Page 1952, Figure 2, “the input image(in the left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where CNN-1 and CNN-M computing a different binary attributes(Attribute 1 and Attribute M) based on the input to CNN-1 and the input to CNN-M corresponds further comprising one or more layers to compute a set of data comprising information to indicate the first subset or the second subset based, at least in part, on the first task descriptor or the second task descriptor as each CNN has layers computing a different binary attribute based on differing and independent inputs and each CNN layer computes it’s own layers to compute different binary attributes (See also Abdulnabi, Page 1955, “After optimizing (2) using the proposed algorithm III-D, the output is the overall model weight matrix , where each column in will be dedicated to its specific corresponding CNN model and is taken back in the backward pass alongside the gradients with respect to its input” where the updated weights during training makes the neural network better at predicting which is considered a more corrected state data to be used to infer respective information(binary attributes)
Regarding claim 27:
Abdulnabi teaches the method of claim 23(and thus the rejection of claim 23 is incorporated)
Abdulnabi teaches wherein the first information inferred by the neural network is inferred using a first set of neurons of the neural network(Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where CNN-1 is considered a first set of neurons of a neural network which infers image information of Attribute 1 using CNN-1 corresponds to a first set of neurons of the neural network) and the second information is inferred by the neural network using a second set of neurons of the neural network different from the first set(Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where CNN-M is considered a second set of neurons of a neural network which infers image information of Attribute M using CNN-M corresponds to a second set of neurons of the neural network that is different from CNN-1)
Regarding claim 28:
Abdulnabi teaches the method of claim 23(and thus the rejection of claim 23 is incorporated)
Abdulnabi teaches further comprising calculating a set of data values to indicate different subsets of the neural network based, at least in part, on input data to the neural network, the different subsets comprising one or more neurons of one or more layers of the neural network to be used to infer respectively different information based, at least in part, on the input data(Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where CNN-1 to CNN-M are considered different CNN’s with convolutional layers that contain different neurons that compute predicting binary attributes (respectively different information))
Regarding claim 29:
Abdulnabi teaches the method of claim 23(and thus the rejection of claim 23 is incorporated)
Abdulnabi teaches further comprising inferring a first output comprising a first of the respectively different information based, at least in part, on a first input comprising a first type of information and inferring a second output comprising a second of the respectively different information based, at least in part, on a second output comprising a second type of information(Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where the output of group1 and groupG are considered a first and second output of a neural network and the output of each respective first and second output are based inferring different information (different binary attributes) of an input image which is considered a first and second input)
Regarding claim 30:
Abdulnabi teaches the method of claim 23(and thus the rejection of claim 23 is incorporated)
Abdulnabi teaches wherein the neural network is a neural coding network comprising one or more convolutional layers to infer respectively different information, (Abdulnabi, Page 1952, Figure 2, where figure 2 shows convolutional layers Conv1-Conv5 that are used to infer) the respectively different information comprising one or more features of image data input to the neural network. (Abdulnabi, Page 1952, Figure 2 description, “the input image (left) with attribute labels information is fed into the model. Each CNN will predict one binary attribute” where the CNN models each predicting a binary attribute of the input image is considered inferring one or more feature of the input image)
Regarding claim 31:
Abdulnabi teaches the method of claim 23(and thus the rejection of claim 23 is incorporated)
Abdulnabi teaches training a first portion of the neural network based, at least in part, on a first set of data; training a second portion of the neural network based, at least in part, on a second set of data; and the first set of data comprises a first type of information and the second set of data comprises a second type of information(Abdulnabi, Page 1950, Col. 1, Paragraph 4, “we train multi-task CNN models together through MTL, where each CNN model is dedicated to learning one binary attribute…we fine-tune a CNN model separately on each attribute annotation to generate attribute-specific features” where CNN models being dedicated to learning one binary attribute is considered training a first and second portion of a neural network on a first and second set of data to infer a first and second type of information respectively)
Response to Arguments
Applicant's arguments filed 04/13/2026 have been fully considered but they are not persuasive. A breakdown for arguments can be found below.
103 Response to Arguments:
Applicant appears to argue that Abdulnabi does not teach to the amended claims "calculate a first task descriptor based, at least in part, on a first input to a neural network implemented using an architecture comprising a plurality of neural network nodes arranged in a series of connected layers; selectively activate, based, at least in part, on the calculated first task descriptor, a first subset of neural network nodes of the architecture of the neural network to infer first information for the first input; calculate a second task descriptor based, at least in part, on a second input to the neural network; and selectively activate, based, at least in part, on the calculated second task descriptor, a second subset of neural network nodes of the architecture of the neural network to infer second information for the second input, wherein at least one neural network node of the architecture is not shared between the first and second subsets” and cites that, in contrast to the claims, Abdulnabi processes the same image through each CNN in parallel and outputs a complete set of attributes for each input image and does not anticipate the current amendments. Specifically, Applicant highlights “a first input, a first subset of the neural network is selectively activated, whereas for a second input based on a different task descriptor a second subset of the neural network is selectively activated to infer different information, where at least one neural network node is not shared between the first and second subsets” as the amendments.
Examiner respectfully disagrees as Examiner finds the current claim language reads on the prior art as the current claims under the broadest reasonable interpretation.
More specifically, “a first input, a first subset of the neural network is selectively activated,” reads on Abdulnabi’s CNN-1 being activated based on the input into CNN-1 that inferred Attribute 1, “whereas for a second input based on a different task descriptor a second subset of the neural network is selectively activated to infer different information,” reads on Abdulnabi’s CNN-M being activated based on the input into CNN-M that infers Attribute M, “where at least one neural network node is not shared between the first and second subsets”, reads on CNN-1 and CNN-M being different CNN’s that has at least one node not shared between them and is part of a larger neural network model.
101 Response to Arguments:
Applicant appears to argue that amended language of “selectively activating, based on calculated respective task descriptors, different portions of a neural network” is not something that can be performed in the human mind.
Examiner agrees with Applicant, however “selectively activating, based on calculated respective task descriptors, different portions of a neural network” was not rejected under a mental process and instead rejected under see MPEP 2106.05(f)).
Applicant appears to argue that a practical application is being addressed in paragraph [0002] of the specification to preserve older knowledge in a neural network to avoid performance degradations.
Examiner respectfully disagrees as the Examiner understands the practical implementation that has been described as the neural networks being used as tools to perform("apply it on a computer" (see MPEP 2106.05(f))), which does not meet the MPEP requirement for practical application. Further, claims that require a computer may still recite a mental process (please see MPEP 2106.04(a)(2).III.C) as the claims appear to recite a generic computer component to transfer/receive information and perform abstract ideas("apply it on a computer" (see MPEP 2106.05(f))) and applicants example does not explain how the additional elements reflect the improvement, or how the improvement is affected by any claimed additional elements. At best applicants example describes in an improvement provided by the claimed abstract idea calculating task descriptors based on respective inputs and inferring respectively information. The claims as presented do not appear to result or highlight an improvement in neural networks or hardware processors and, although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims(see In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Examiner notes MPEP 2106.05(a) which provides the requirements for how an improvement to the functioning of a computer or to any other technology or technical field is evaluated.
Applicant appears to argue that the current claims overcome 101 in view of Ex Parte Desjardins et al.
Examiner respectfully disagrees as there are no claims that positively recite a limitation that reflect an improvement or practical application unlike in Ex Parte Desjardins the specific continual-learning parameter preservation mechanism of training on a second task using posterior distribution from the first task in the claim as reflecting the improvement.
Conclusion
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 CHARLES JEFFREY JONES JR whose telephone number is (703)756-1414. The examiner can normally be reached Monday - Friday 8:00 - 5:00 EST.
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, Kakali Chaki can be reached at 571-272-3719. 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.
/C.J.J./Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122
Prosecution Insights