DETAILED ACTION
This Office Action is sent in response to Applicant’s Communication received 2/27/2024 for application number 18/589,092.
Claims 1-20 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 § 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, 9-10, and 13-20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Wang et al. (US 2021/0125070 A1).
In reference to claim 1, Wang discloses a computer implemented method of compressing a neural network (para. 0005), the method comprising: receiving a neural network (neural network is trained, para. 0081); determining a matrix representative of a set of coefficients of a layer of the received neural network, the layer being arranged to perform an operation, the matrix comprising a plurality of elements representative of non-zero values and a plurality of elements representative of zero values (filter / kernel layer of CNN is turned into 2D matrix, para 0057-59, 0081); rearranging the rows and/or columns of the matrix so as to gather the plurality of elements representative of non-zero values of the matrix into one or more sub-matrices, the one or more sub-matrices having a greater number of elements representative of non-zero values per total number of elements of the one or more sub-matrices than the number of elements representative of non-zero values per total number of elements of the matrix (columns are swapped to produce more sub-matrices that are blocks of all zeroes, para. 0081); and outputting a compressed neural network comprising a compressed layer arranged to perform a compressed operation in dependence on the one or more sub-matrices (once compressed, the neural network can be used to perform an inference with the sub-matrices, para. 0081-84).
In reference to claim 2, Wang discloses the method of claim 1, wherein each of the one or more sub-matrices has a greater number of elements representative of non-zero values per total number of elements of that sub-matrix than the number of elements representative of non-zero values per total number of elements of the matrix (blocks have all zero values, para. 0081).
In reference to claim 3, Wang discloses the method of claim 1, wherein the matrix comprises the set of coefficients of the layer, the plurality of elements representative of non-zero values are a plurality of non-zero coefficients, the plurality of elements representative of zero values are a plurality of zero coefficients, and the one or more sub-matrices comprise a subset of the set of coefficients of the layer (matrix is zero or nonzero values of weights, i.e. coefficients, of filter, and the blocks are subsets of the weights, para 0057-59, 0081).
In reference to claim 4, Wang discloses the method of claim 3, wherein: the layer of the received neural network is arranged to perform the operation by performing a matrix multiplication using the matrix comprising the set of coefficients of the layer and an input matrix comprising a set of input activation values of the layer; and the compressed neural network is configured such that the compressed layer is arranged to perform the compressed operation by performing one or more matrix multiplications using the one or more sub-matrices comprising the subset of the set of coefficients of the layer and one or more input sub-matrices each comprising a respective subset of the set of input activation values of the layer (see para. 0057-71 and para. 0084: matrix input and filter are multiplied by multiplying the respective sub-matrices).
In reference to claim 9, Wang discloses the method of claim 1, wherein the matrix representative of the set of coefficients of the layer of the received neural network does not have sub-graph separation (initially received neural network is not already separated, para 0057-59, 0081).
In reference to claim 10, Wang discloses the method of claim 1, further comprising rearranging the rows and/or columns of the matrix so as to form a rearranged matrix including: one or more block arrays which are arranged along a diagonal of the rearranged matrix, and/or one or more block arrays which are not arranged along a diagonal of the rearranged matrix; and one or more horizontal arrays which are horizontally arranged across the rearranged matrix, and/or one or more vertical arrays which are vertically arranged across the rearranged matrix (non-diagonal blocks, para. 0081).
In reference to claim 13, Wang discloses the method of claim 1, further comprising storing the compressed neural network for subsequent implementation (compressed network is stored with reduced storage size, para. 0057).
In reference to claim 14, Wang discloses the method of claim 1, further comprising outputting a computer readable description of the compressed neural network that, when implemented at a system for implementing a neural network, causes the compressed neural network to be executed (compressed network is stored with reduced storage size for execution, para. 0057, 0084).
In reference to claim 15, Wang discloses the method of claim 1, further comprising configuring hardware logic to implement the compressed neural network, optionally wherein the hardware logic comprises a neural network accelerator (para. 0046).
In reference to claim 16, Wang discloses the method of claim 1, further comprising using the compressed neural network to perform image processing (para. 0054).
In reference to claim 17, Wang discloses the method of claim 1, further comprising receiving the neural network comprising the layer arranged to perform the operation using the set of coefficients, wherein the one or more sub-matrices are representative of a subset of the set of coefficients of the layer of the received neural network, and the compressed layer is arranged to perform the compressed operation using the subset of the set of coefficients of the layer of the received neural network (see para. 0057-71 and para. 0084: matrix input and filter are multiplied by multiplying the respective sub-matrices).
In reference to claim 18, Wang discloses the method of claim 17, wherein the subset of the set of coefficients of the layer of the received neural network comprises all of the non-zero coefficients of the set of coefficients of the layer of the received neural network, and the other coefficients of the set of coefficients not comprised by the subset are exclusively zero coefficients, such that no information is lost by the compressed layer being arranged to perform the compressed operation without using the other coefficients of the set of coefficients not comprised by the subset (some blocks have nonzero values, and the other blocks have all zero values, para. 0081; multiplication performed on the non-zero blocks, para. 0057-71 and para. 0084).
In reference to claim 19, this claim is directed to a system associated with the method claimed in claim 1 and is therefore rejected under a similar rationale.
In reference to claim 20, this claim is directed to a non-transitory computer readable medium associated with the method claimed in claim 1 and is therefore rejected under a similar rationale.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 5-7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. (US 2021/0125070 A1) as applied to claim 1 above, and further in view of You et al. (US 10,970,619 B1).
In reference to claim 5, Wang teaches the method of claim 1, wherein the layer of the received neural network is a convolution layer comprising a set of coefficients arranged in one or more filters (filter / kernel of layer of CNN is a plurality of weights, or coefficients, para 0057-59, 0081) for each input … of each filter: determining whether that input …. of that filter comprises a non-zero coefficient; and in response to determining that that input … of that filter comprises at least one non-zero coefficient, representing that input … of that filter with an element representative of a non-zero value in the matrix; or in response to determining that that input … of that filter comprises exclusively zero coefficients, representing that input … of that filter with an element representative of a zero value in the matrix (elements can be marked as all zero or nonzero, para. 0081).
However, Wang does not explicitly teach each of the one or more filters arranged in one or more input channels.
You teaches each of the one or more filters arranged in one or more input channels, each input channel of each filter comprising a respective subset of the set of coefficients of the convolution layer (kernels are arranged in channels, which channels comprising subset of weights in kernel, para. 0077-89).
It would have been obvious to one of ordinary skill in art, having the teachings of Wang and You before the earliest effective filing date, to modify the CNN of Wang to include the channels of You.
One of ordinary skill in the art would have been motivated to modify the CNN of Wang to include the channels of You because it would allow the image processing CNN of Wang to work more image data, like colors.
In reference to claim 6, You teaches the method of claim 5, wherein each row of the matrix is representative of a filter of the one or more filters of the convolution layer, and each column of the matrix is representative of an input channel of the one or more input channels of the convolution layer (see para. 0089: number of rows corresponding to filters and number of columns correspond to channels).
In reference to claim 7, Wang and You teach the method of claim 5, wherein: the convolution layer of the received neural network is arranged to perform the operation by convolving a set of input activation values of the convolution layer with the set of coefficients of the convolution layer; the one or more sub-matrices comprise a plurality of elements representative of a subset of the input channels of the filters of the set of coefficients of the convolution layer; and the compressed neural network is configured such that the compressed layer is arranged to perform the compressed operation by convolving one or more subsets of input activation values of the convolution layer with the subset of the set of coefficients of the convolution layer comprised by the one or more subsets of the input channels of the filters represented by elements in the one or more sub-matrices (Wang teaches compressed convolution performed with blocks, para. 0057-71 and para. 0084, and You teaches channels, para. 0077-89).
Claim(s) 8 and 11-12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. (US 2021/0125070 A1) as applied to claim 1 above, and further in view of Aykanat et al., Permuting sparse rectangular matrices into block-diagonal form (NPL [U], See Notice of References Cited).
In reference to claim 8, Wang does not explicitly teach the method of claim 1, further comprising: forming a hypergraph model in dependence on the respective row and column position of each of the plurality of elements representative of non-zero values within the matrix; partitioning the hypergraph model; and rearranging the rows and/or columns of the matrix in dependence on the partitioned hypergraph model so as to gather the plurality of elements representative of non-zero values of the matrix into the one or more sub-matrices.
Aykanat teaches the method of claim 1, further comprising: forming a hypergraph model in dependence on the respective row and column position of each of the plurality of elements representative of non-zero values within the matrix; partitioning the hypergraph model; and rearranging the rows and/or columns of the matrix in dependence on the partitioned hypergraph model so as to gather the plurality of elements representative of non-zero values of the matrix into the one or more sub-matrices (Aykanat teaches using a hypergraph model to partition a sparse graph into a singly bordered block-diagonal form, particularly see pages 1860 and 1865-70).
It would have been obvious to one of ordinary skill in art, having the teachings of Wang and Aykanat before the earliest effective filing date, to modify the rearranging of Wang to include the hypergraph partitioning of Aykanat.
One of ordinary skill in the art would have been motivated to modify the rearranging of Wang to include the hypergraph partitioning of Aykanat because it allows rearranging of sparse matrices using common tools in a computational efficient form (Aykanat, pages 1861-64).
In reference to claim 11, Wang does not explicitly teach the method of claim 1, further comprising rearranging the rows and/or columns of the matrix so as to form a rearranged matrix that is in bordered block matrix form; or a rearranged matrix that is a block matrix comprising arrays that are permutable into bordered block matrix form.
Aykanat teaches the method of claim 1, further comprising rearranging the rows and/or columns of the matrix so as to form a rearranged matrix that is in bordered block matrix form; or a rearranged matrix that is a block matrix comprising arrays that are permutable into bordered block matrix form (singly bordered block-diagonal form, particularly see pages 1860 and 1865-70).
It would have been obvious to one of ordinary skill in art, having the teachings of Wang and Aykanat before the earliest effective filing date, to modify the rearranging of Wang to include the block diagonal matrix of Aykanat.
One of ordinary skill in the art would have been motivated to modify the rearranging of Wang to include the block diagonal matrix of Aykanat because it allows rearranging of sparse matrices using common tools in a computational efficient form (Aykanat, pages 1861-64).
In reference to claim 12, Wang does not explicitly teach the method of claim 1, further comprising rearranging the rows and/or columns of the matrix so as to convert the matrix into bordered block matrix form, optionally comprising rearranging the rows and/or columns of the matrix so as to convert the matrix into singly-bordered block-diagonal matrix form.
Aykanat teaches the method of claim 1, further comprising rearranging the rows and/or columns of the matrix so as to convert the matrix into bordered block matrix form, optionally comprising rearranging the rows and/or columns of the matrix so as to convert the matrix into singly-bordered block-diagonal matrix form (singly bordered block-diagonal form, particularly see pages 1860 and 1865-70).
It would have been obvious to one of ordinary skill in art, having the teachings of Wang and Aykanat before the earliest effective filing date, to modify the rearranging of Wang to include the block diagonal matrix of Aykanat.
One of ordinary skill in the art would have been motivated to modify the rearranging of Wang to include the block diagonal matrix of Aykanat because it allows rearranging of sparse matrices using common tools in a computational efficient form (Aykanat, pages 1861-64).
Conclusion
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