DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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)(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, 4, 6, 15, 18, and 20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Cummings et al (US 2022/027792, hereafter Cummings).
As per claim 1, Cummings discloses a method for searching for a neural network architecture ensemble model, wherein the method comprises:
obtaining a dataset, wherein the dataset comprises a sample and an annotation in a classification task (¶ 26);
performing search by using a distributional neural network architecture search algorithm, comprising:
determining a hyperparameter of a neural network architecture distribution (¶ 23 and 30);
sampling a neural network architecture from the architecture distribution defined by the hyperparameter (¶ 30);
training and evaluating the neural network architecture, based on the sample and the annotation in the classification task, to obtain a performance indicator (¶ 50 and 66);
determining, based on the performance indicator, predicted neural network architecture distributions that share the hyperparameter- to obtain a candidate pool of base learners, wherein a base learner is a neural network architecture that meets an architecture distribution requirement, and the neural network architecture is formed by repeatedly stacking neural network architecture cells (¶ 76); and
determining a surrogate model, wherein the surrogate model is used to predict test performance of an unevaluated neural network architecture; and predicting test performance of a base learner in the candidate pool by using the surrogate model, and determining that k base learners that meet a requirement of the classification task form an ensemble model, wherein a size of the ensemble model is k (¶ 41 - 45).
As per claim 4, Cummings discloses the method of claim 1, wherein the determining a hyperparameter of a neural network architecture distribution comprises:
optimizing the hyperparameter of the neural network architecture distribution by using a search policy, wherein the search policy is Bayesian optimization, and the search policy is used to sample, in a next iteration, a neural network cell whose performance indicator better meets a requirement than that of a current neural network architecture cell (¶ 44 and 76).
As per claim 6, Cummings discloses the method of claim 1, wherein the training and evaluating the neural network architecture
training the neural network architecture on a training dataset; and evaluating the neural network architecture on a validation dataset; to obtain the performance indicator, wherein both training set data and validation set data belong to the dataset (¶ 26 and 27).
Regarding claim 15, arguments analogous to those presented for claim 1 are applicable for claim 15.
Regarding claim 18, arguments analogous to those presented for claim 4 are applicable for claim 18.
Regarding claim 20, arguments analogous to those presented for claim 6 are applicable for claim 20.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cummings in view of Czarnecki et al (US 11,113,605, hereafter Czarnecki).
As per claim 7, Cummings discloses the method of claim 1.
However, Cummings does not explicitly teach wherein the performing search by using a distributional neural network architecture search (distributional NAS) algorithm further comprises: determining a search policy for the neural network architecture distribution based on the performance indicator and the hyperparameter of the predicted neural network architecture distribution.
In the same field of endeavor, Czarnecki teaches wherein the performing search by using a distributional neural network architecture search (distributional NAS) algorithm further comprises: determining a search policy for the neural network architecture distribution based on the performance indicator and the hyperparameter of the predicted neural network architecture distribution (column 2 lines 12 – 30).
Therefore, it would have been obvious for one of ordinary skill in the art at the time the invention was effectively filed to modify the invention of Cummings in view of Czarnecki. The advantage is an improved neural network.
Claim(s) 8 and 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cummings in view of Nair et al (US 11,650,968, hereafter Nair).
As per claim 8, Cummings discloses the method of claim 1.
However, Cummings does not explicitly teach wherein the performing search by using a distributional neural network architecture search (distributional NAS) algorithm further comprises: determining a predicted performance value of a hyperparameter of another unknown distribution, comprising a mean value and a variance, based on a hyperparameter and a performance indicator of each found neural network architecture distribution; and determining a performance prediction policy for the neural network architecture distribution based on the mean value and the variance, wherein the performance prediction policy is used to predict the performance indicator of the neural network architecture distribution.
In the same field of endeavor, Nair teaches wherein the performing search by using a distributional neural network architecture search (distributional NAS) algorithm further comprises: determining a predicted performance value of a hyperparameter of another unknown distribution, comprising a mean value and a variance, based on a hyperparameter and a performance indicator of each found neural network architecture distribution; and determining a performance prediction policy for the neural network architecture distribution based on the mean value and the variance, wherein the performance prediction policy is used to predict the performance indicator of the neural network architecture distribution (column 12 lines 50 – 67, column 13 lines 43 - 54, Table 3).
Therefore, it would have been obvious for one of ordinary skill in the art at the time the invention was effectively filed to modify the invention of Cummings in view of Nair. The advantage is improving training a neural network.
As per claim 9, Cummings discloses the method of claim 1.
However, Cummings does not explicitly teach wherein the determining, based on the performance indicator, neural network architecture distributions that share the hyperparameter; to obtain a candidate pool of base learners comprises: determining a search policy for the neural network architecture distribution based on the performance indicator and the hyperparameter; determining a performance prediction policy for the neural network architecture distribution based on the performance indicator and a neural network architecture cell; and searching, according to the search policy and the performance prediction policy, the neural network architecture distributions that share the hyperparameter, to determine the candidate pool of the base learners.
In the same field of endeavor, Nair teaches wherein the determining, based on the performance indicator, neural network architecture distributions that share the hyperparameter; to obtain a candidate pool of base learners comprises: determining a search policy for the neural network architecture distribution based on the performance indicator and the hyperparameter; determining a performance prediction policy for the neural network architecture distribution based on the performance indicator and a neural network architecture cell; and searching, according to the search policy and the performance prediction policy, the neural network architecture distributions that share the hyperparameter, to determine the candidate pool of the base learners (column 12 lines 50 – 67, column 13 lines 43 - 54, Table 3).
Therefore, it would have been obvious for one of ordinary skill in the art at the time the invention was effectively filed to modify the invention of Cummings in view of Nair. The advantage is improving training a neural network.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cummings in view of Xue et al (US 2022/0027739, hereafter Xue).
As per claim 10, Cummings discloses the method of claim 1.
However, Cummings does not explicitly teach wherein the determining, based on the performance indicator, neural network architecture distributions that share the hyperparameter; to obtain a candidate pool of base learners comprises: outputting, based on a plurality of neural network architectures in a historical search and corresponding performance indicators, a plurality of neural network architectures that share the hyperparameter; determining, based on the plurality of neural network architectures that share the hyperparameter, a neural network architecture distribution that meets a requirement; and generating a plurality of neural network architecture cells based on the neural network architecture distribution that meets the requirement, to obtain a generation distribution/the candidate pool of the base learners.
In the same field of endeavor, Xue teaches wherein the determining, based on the performance indicator, neural network architecture distributions that share the hyperparameter; to obtain a candidate pool of base learners comprises: outputting, based on a plurality of neural network architectures in a historical search and corresponding performance indicators, a plurality of neural network architectures that share the hyperparameter; determining, based on the plurality of neural network architectures that share the hyperparameter, a neural network architecture distribution that meets a requirement; and generating a plurality of neural network architecture cells based on the neural network architecture distribution that meets the requirement, to obtain a generation distribution/the candidate pool of the base learners (¶ 16).
Therefore, it would have been obvious for one of ordinary skill in the art at the time the invention was effectively filed to modify the invention of Cummings in view of Xue. The advantage is optimizing selecting a hyperparameter.
Claim(s) 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cummings in view of Shahrzad et al (US 11,75,841, hereafter Shahrzad).
As per claim 11, Cummings discloses the method of claim 1.
However, Cummings does not explicitly teach wherein the determining a surrogate model comprises: obtaining the surrogate model through training on the dataset based on the neural network architecture cells and the performance indicator.
In the same field of endeavor, Shahrzad teaches wherein the determining a surrogate model comprises: obtaining the surrogate model through training on the dataset based on the neural network architecture cells and the performance indicator (column 5 lines 3 – 26).
Therefore, it would have been obvious for one of ordinary skill in the claim at the time the invention was effectively filed to modify the invention of Cummings in view of Shahrzad. The advantage is achieving better outcomes and trustworthiness.
Claim(s) 12 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cummings in view of Rawat et al (US 2022/01998222, hereafter Rawat).
As per claim 12, Cummings discloses the method of claim 1.
However, Cummings does not explicitly teach wherein the predicting test performance of the base learner in the candidate pool by using the surrogate model, and determining that k base learners that meet a task scenario requirement form an ensemble model comprises: predicting test performance of a plurality of base learners in the candidate pool by using the surrogate model; performing local search based on a prediction result, and determining q estimated vertex architectures, wherein an estimated vertex architecture is a neural network architecture whose performance indicator predicted by the surrogate model on a validation set is higher than that of an adjacent architecture; and combining k architectures whose performance indicators meet the requirement in the q estimated vertex architectures- to obtain the ensemble model.
In the same field of endeavor, Rawat teaches wherein the predicting test performance of the base learner in the candidate pool by using the surrogate model, and determining that k base learners that meet a task scenario requirement form an ensemble model comprises: predicting test performance of a plurality of base learners in the candidate pool by using the surrogate model; performing local search based on a prediction result, and determining q estimated vertex architectures, wherein an estimated vertex architecture is a neural network architecture whose performance indicator predicted by the surrogate model on a validation set is higher than that of an adjacent architecture; and combining k architectures whose performance indicators meet the requirement in the q estimated vertex architectures- to obtain the ensemble model (¶ 3, 25, and 49).
Therefore, it would have been obvious for one of ordinary skill in the claim at the time the invention was effectively filed to modify the invention of Cummings in view of Rawat. The advantage is selecting an improved ensemble model.
As per claim 13, Cummings discloses the method of claim 12.
However, Cummings does not explicitly teach wherein the combining k architectures whose performance indicators meet the requirement in the q estimated vertex architectures comprises: sorting performance indicators of the q estimated vertex architectures in descending order, and combining k architectures whose performance indicators rank top.
In the same field of endeavor, Rawat teaches teach wherein the combining k architectures whose performance indicators meet the requirement in the q estimated vertex architectures comprises: sorting performance indicators of the q estimated vertex architectures in descending order, and combining k architectures whose performance indicators rank top (¶ 3, 25, and 49).
Therefore, it would have been obvious for one of ordinary skill in the claim at the time the invention was effectively filed to modify the invention of Cummings in view of Rawat. The advantage is selecting an improved ensemble model.
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Cummings in view of Rawat (hereafter Cummings) in further view of MacWilliams et al (US 2024/0169272, hereafter MacWilliams).
As per claim 14, Cummings discloses the method of claim 12.
However, Cummings does not explicitly teach wherein the combining k architectures whose performance indicators meet the requirement in the q estimated vertex architectures comprises: traversing the q estimated vertex architectures by using a greedy algorithm, and adding the k architectures one by one to form the ensemble model.
In the same field of endeavor, MacWilliams teaches wherein the combining k architectures whose performance indicators meet the requirement in the q estimated vertex architectures comprises: traversing the q estimated vertex architectures by using a greedy algorithm, and adding the k architectures one by one to form the ensemble model (¶ 82).
Therefore, it would have been obvious for one of ordinary skill in the claim at the time the invention was effectively filed to modify the invention of Cummings in view of Rawat in further view of MacWilliams. The advantage is selecting an improved ensemble model.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHIKAODILI E ANYIKIRE whose telephone number is (571)270-1445. The examiner can normally be reached 8 am - 4:30 pm.
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, David Czekaj can be reached at 571-272-7327. 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.
/CHIKAODILI E ANYIKIRE/Primary Examiner, Art Unit 2487
Prosecution Insights