DETAILED ACTION
This Office Action is sent in response to Applicant’s Communication received 12/28/2023 for application number 18/399,651.
Claims 1-15 are pending.
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 § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 3, 9, and 10 are 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. Claims 3, 9, and 10 recite, “the user tensor.” Parent claim 1 recites two different user tensors (one outputted by a last layer of the compiled neural network, and one outputted by a sub-network); it is not clear which user tensor this limitation is referring to. For prior art, the Examiner is assuming the term is referring to the second user tensor outputted by a sub-network.
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)(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.
Claim(s) 1-15 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Liu et al., NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers (NPL [U], see Notice of References Cited).
In reference to claim 1, Liu discloses a method for reducing a neural network comprising: compiling the neural network by a reference compiler to rearrange reference weights; manipulating a reference tensor inputted to the neural network with the reference weights to output a reference tensor for each layer of the neural network (an initial reference implementation of a neural network is compiled to obtain reference input and output tensors, 2. Background, pages 531-32); compiling the neural network by a user compiler to rearrange user weights (user-specified DNN is compiled, 2.2 DL compilers, page 532, and 3. NNSmiths Design, pages 533-34); manipulating the reference tensor inputted to the neural network with the user weights to output a user tensor for the neural network; if a reference tensor of a last layer of the neural network is inconsistent with the user tensor (tensor inputs and output are compared to see if the compiled model is consistent, i.e. numerically valid, with reference model, Challenge #3, page 532-33, and 3.3 Improving Numeric Validity with Gradient, pages 535-36), then a network reducer sorting and partitioning the neural network into a plurality of sub-networks each containing at least one layer; compiling the plurality of sub-networks to rearrange user weights of the sub-networks; and manipulating a reference tensor inputted to a corresponding sub-network with corresponding user weights to output a user tensor (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 2, Liu discloses the method of claim 1 wherein the network reducer partitions the neural network into the plurality of sub-networks according to a result of sorting the neural network (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 3, Liu discloses the method of claim 1 further comprising if the user tensor is inconsistent with a corresponding reference tensor, the network reducer partitioning the sub-network into a plurality of minor sub-networks each containing at least one layer (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 4, Liu discloses the method of claim 1 further comprising obtaining a directed acyclic graph (DAG) representation of the neural network (graph representation of DNN is created, 3.2 Model Generation, pages 533-34; graph of DNN would be a DAG).
In reference to claim 5, Liu discloses the method of claim 4 wherein the network reducer sorts the neural network by performing a topological sort on the DAG representation to obtain a sorted list (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 6, Liu discloses the method of claim 5 wherein the network reducer partitioning the neural network into a plurality of sub-networks is the network reducer partitioning the sorted list into two subsequences (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 7, Liu discloses the method of claim 6 wherein compiling the plurality of sub-networks to rearrange the user weights of the sub-networks is compiling the two subsequences to rearrange user weights of the two subsequences (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 8, Liu discloses the method of claim 7 wherein manipulating the reference tensor inputted to the corresponding sub-network with the corresponding user weights to output the user tensor is running a subsequence with the reference tensor and the corresponding user weights to output the user tensor (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 9, Liu discloses the method of claim 1 further comprising if the user tensor is inconsistent with a corresponding reference tensor, and the network reducer is unable to further partition the sub-network, then outputting the sub-network to a data reducer (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 10, Liu discloses the method of claim 9 further comprising choosing part of the user tensor as golden (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 11, Liu discloses the method of claim 9 further comprising the data reducer simplifying the reference tensor inputted to the corresponding sub-network and simplifying corresponding user weights (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 12, Liu discloses the method of claim 11 wherein the data reducer simplifying the reference tensor inputted to the corresponding sub-network and simplifying the corresponding user weights comprises: identifying which of the corresponding user weights are redundant weights; and flipping the redundant weights to zeros (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 13, Liu discloses the method of claim 12 wherein the redundant weights are identified one by one in a topological order(the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 14, Liu discloses the method of claim 12 wherein the redundant weights are identified one by one in a reverse topological order (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
In reference to claim 15, Liu discloses the method of claim 12 wherein identifying which of the corresponding user weights are redundant weights is performed by using a region of interest (ROI) mask and a differential test (the Examiner notes that this is a “contingent limitation,” and therefore, “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” See MPEP 2111.04(II). Here, the BRI of the claim is that these limitations do not need to be performed when the reference and user tensors are consistent).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Chen et al., DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization (NPL [V]) which teaches a neural network compiler dividing a network into subnetworks, Guo et al. (NPL [W]) which teaches locating bugs in a particular layer of a DNN for deep learning frameworks; the remaining references generally teach background information on neural network compilation and bug detection.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Andrew T. Chiusano whose telephone number is (571)272-5231. The examiner can normally be reached M-F, 10am-6pm.
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, Tamara Kyle can be reached at 571-272-4241. 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.
/ANDREW T CHIUSANO/Primary Examiner, Art Unit 2144
Prosecution Insights