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)(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.
Claims 1-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Csefalvay (US 2020/0202218 A1), hereinafter “Csefalvay”.
As per claim 1, Csefalvay teaches a method of identifying one or more quantisation parameters for transforming values to be processed by a Neural Network (NN) for implementing the NN in hardware comprising:
“determining an output of a model of the NN in response to training data, the model of the NN comprising one or more quantisation blocks, each of the quantisation blocks being configured to transform one or more set of values input to a layer of the NN to respective fixed point number format defined by one or more quantisation parameters prior to the model processing that one or more set of values in accordance with the layer” at [0015], [0053]-[0058] and Figs. 4-5;
(Csefalvay teaches determining an output of a model of the DNN in response to training data, the model of the DNN comprising a quantisation block configured to transform a set of values input to a layer of the DNN prior to the model processing the set of values in accordance with the layer, the transformation of the set of values simulating quantisation of the set of values to a fixed point number format defined by one or more quantisation parameters)
“determining a cost metric of the NN that is a combination of an error metric and an implementation metric, the implementation metric being representative of an implementation cost of the NN based on the one or more quantisation parameter according to the one or more sets of values have been transformed”
(Csefalvay teaches determining a cost metric of the DNN that is a combination of an error metric and a size metric, the size metric being proportional to a size of the DNN based on the one or more quantisation parameters)
“the implement metric being dependent on, for each of a plurality of layers of the NN: a first contribution representative of an implementation cost of an output from that layer, and a second distribution representative of an implementation cost of an output from a layer preceding that layer” at [0072]-[0078] and Fig. 4.
(Csefalvay teaches the size metric sm is the size of the DNN, which is the number of bits or bytes used to represent the values of the DNN, wherein the DNN comprises a plurality of layers, each layer includes quantized input data values and quantized output data value. The size metric of Layer 2 is therefore dependent on the size of quantized output from Layer 2 and the quantized output of preceding layer 1)
“back-propagating a derivative of the cost metric to at least one of the one or more quantisation parameters to generate a gradient of the cost metric for the at least one of the one or more quantisation parameters” at [0015]
(Csefalvay teaches back-propagating a derivative of the cost metric to at least one of the one or more quantisation parameters to generate a gradient of the cost metric for the at least one of the one or more quantisation parameters)
“adjusting the at least one of the one or more quantisation parameters based on the gradient for the at least one of the one or more quantisation parameters” at [0015].
(Csefalvay teaches adjusting the at least one of the one or more quantisation parameters based on the gradient for the at least one of the one or more quantisation parameters)
As per claim 2, Csefalvay teaches the method of claim 1, further comprising “subsequent to the adjusting step (d), removing a set of values from the model of the NN in dependence on the adjusted at least one of the one or more quantisation parameters” at [0010]-[0011].
As per claim 3, Csefalvay teaches the method of claim 1, wherein “the first contribution is formed in dependence on an implementation cost of one or more output channels of weight data input to the layer, and the second contribution is formed in dependence on an implementation cost of one or more input channels of activation data input to the layer” at [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 4, Csefalvay teaches the method of claim 1, wherein “the first contribution is formed in dependence on an implementation cost of one or more output channels of weight data input to the layer, and the second contribution is formed in dependence on an implementation cost of one or more input channels of weight data input to the layer” at [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 5, Csefalvay teaches the computer-implemented method of claim 1, wherein “each of the one or more quantisation parameters includes a respective bit width, and wherein each of the one or more sets of values is a channel of values input to the layer, the method comprising determining a respective bit width for each of one or more input channels of weight data input to the layer and determining a respective bit width for each of one or more output channels of weight data input to the layer” at [0040]-[0046], [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 6, Csefalvay teaches the computer-implemented method of claim 5, wherein “a first bit width and a second bit width is determined, respectively, for each weight value input to the layer, and the method comprises transforming each weight value input to the layer according to its respective first and/or second bit width, optionally the smaller of its respective first and second bit widths” at [0040]-[0046], [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 7, Csefalvay teaches the computer-implemented method of claim 5, the method comprising, “subsequent to the adjusting step (d), removing from the model of the NN an output channel of the weight data input to the preceding layer when the adjusted bit width for a corresponding input channel of the weight data input to the layer is zero” at [0040]-[0046], [0049]-[0050],[0072]-[0078].
As per claim 8, Csefalvay teaches the computer-implemented method of claim 1, wherein: “the first contribution is formed in dependence on an implementation cost of one or more output channels of weight data input to the layer and an implementation cost of one or more biases input to the layer; and the second contribution is formed in dependence on an implementation cost of one or more output channels of weight data input to the preceding layer and an implementation cost of one or more biases input to the preceding layer” at [0040]-[0046], [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 9, Csefalvay teaches the computer-implemented method of claim 1, wherein “the first contribution is formed in dependence on an implementation cost of one or more output channels of weight data input to the layer, and the second contribution is formed in dependence on an implementation cost of one or more output channels of weight data input to the preceding layer” at [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 10, Csefalvay teaches the computer-implemented method of claim 1, wherein “each of the one or more quantisation parameters includes a respective bit width, and wherein the one or more sets of values include one or more output channels of weight data input to the layer and one or more output channels of weight data input to the preceding layer, the method comprising transforming each of the one or more output channels of weight data input to the layer according to a respective bit width, and transforming each of the one or more output channels of weight data input to the preceding layer according to a respective bit width” at [0040]-[0046], [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 11, Csefalvay teaches the computer-implemented method of claim 10, the method further comprising, “subsequent to the adjusting step (d), removing from the model of the NN an output channel of the weight data input to the preceding layer when the adjusted bit width for that output channel is zero” at [0040]-[0046], [0049]-[0050],[0072]-[0078].
As per claim 12, Csefalvay teaches the computer-implemented method of claim 9, wherein “the implementation metric is further dependent on, for each of a plurality of layers of the NN, a further contribution representative of an implementation cost of one or more biases input to the preceding layer” at [0007]-[0010], [0048]-[0050],[0072]-[0078].
As per claim 13, Csefalvay teaches the computer-implemented method of claim 12, the method further comprising, “subsequent to the adjusting step (d), removing from the model of the NN an output channel of the weight data input to the preceding layer when the adjusted bit width for that output channel and the absolute value of its associated bias is zero” at [0007]-[0010], [0048]-[0050],[0072]-[0078].
As per claim 14, Csefalvay teaches the computer implemented method of claim 1, wherein “a layer of the NN receives activation input data that has been derived from the activation output data of more than one preceding layer, and wherein the implementation metric for that layer is dependent on: a first contribution representative of an implementation cost of an output from that layer; a second contribution representative of an implementation cost of an output from a first layer preceding that layer; and a third contribution representative of an implementation cost of an output from a second layer preceding that layer” at [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 15, Csefalvay teaches the computer implemented method of claim 1, wherein “a layer of the NN outputs activation data that is input to a first subsequent layer and to a second subsequent layer, wherein the method further comprises adding a new layer to the NN between the layer and the first subsequent layer, and wherein the implementation metric for the first subsequent layer is dependent on: a first contribution representative of an implementation cost of an output from the first subsequent layer; and a second contribution representative of an implementation cost of an output from the new layer” at [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 16, Csefalvay teaches the computer-implemented method of claim 1, wherein “the second contribution is representative of an implementation cost of an output from a layer immediately preceding that layer” at [0049]-[0050],[0072]-[0078] and Fig. 4.
As per claim 17, Csefalvay teaches the computer-implemented method of claim 1, further comprising “outputting the adjusted the at least one of the one or more quantisation parameters for use in configuring hardware logic to implement the NN” at [0111] and Fig. 10.
As per claim 18, teaches the computer-implemented method of claim 1, further comprising “configuring hardware logic to implement the NN using the adjusted quantisation parameters, optionally wherein the hardware logic comprises a neural network accelerator” at [0111] and Fig. 10
Claim 19-20 recite similar limitations as in claim 1 and are therefore rejected by the same reasons.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims1-20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-20 of US Patent No. 11,610,127. Although the claims at issue are not identical, they are not patentably distinct from each other because Claims 1-20 of US Patent No. 11,610,127 contain every element of claims 1-20 of the instant application, as detailed in the mapping table below, and as such anticipate claims 1-20 of the instant application.
“A later patent claim is not patentably distinct from an earlier patent claim if the later claim is obvious over, or anticipated by, the earlier claim. In re Longi, 759 F.2d at 896, 225 USPQ at 651 (affirming a holding of obviousness-type double patenting because the claims at issue were obvious over claims in four prior art patents); In re Berg, 140 F.3d at 1437, 46 USPQ2d at 1233 (Fed. Cir. 1998) (affirming a holding of obviousness-type double patenting where a patent application claim to a genus is anticipated by a patent claim to a species within that genus). “ELI LILLY AND COMPANY v BARR LABORATORIES, INC., United States Court of Appeals for the Federal Circuit, ON PETITION FOR REHEARING EN BANC (DECIDED: May 30, 2001).
Instant Application 18/216,461
Patent No. 11,610,127
1.A computer-implemented method of identifying one or more quantisation parameters for transforming values to be processed by a Neural Network (NN) for implementing the NN in hardware, the method comprising, in at least one processor:
(a) determining an output of a model of the NN in response to training data, the model of the NN comprising one or more quantisation blocks, each of the one or more quantisation blocks being configured to transform one or more sets of values input to a layer of the NN to a respective fixed point number format defined by one or more quantisation parameters prior to the model processing that one or more sets of values in accordance with the layer;
(b) determining a cost metric of the NN that is a combination of an error metric and an implementation metric, the implementation metric being representative of an implementation cost of the NN based on the one or more quantisation parameters according to which the one or more sets of values have been transformed, the implementation metric being dependent on, for each of a plurality of layers of the NN: a first contribution representative of an implementation cost of an output from that layer; and a second contribution representative of an implementation cost of an output from a layer preceding that layer; (c) back-propagating a derivative of the cost metric to at least one of the one or more quantisation parameters to generate a gradient of the cost metric for the at least one of the one or more quantisation parameters; and
(d) adjusting the at least one of the one or more quantisation parameters based on the gradient for the at least one of the one or more quantisation parameters.
1.A computer-implemented method to configure hardware to implement a Deep Neural Network (DNN), the method comprising, in at least one processor:
(a) determining an output of a model of the DNN in response to training data, the model of the DNN comprising a quantisation block configured to transform a set of values input to a layer of the DNN prior to the model processing the set of values in accordance with the layer, the transformation of the set of values simulating quantisation of the set of values to a fixed point number format defined by one or more quantisation parameters;
(b) determining a cost metric of the DNN that is a combination of an error metric and a size metric, the error metric being a quantitative measure of an error in the determined output, and the size metric being proportional to a size of the DNN based on the one or more quantisation parameters;
(c) back-propagating a derivative of the cost metric to at least one of the one or more quantisation parameters to generate a gradient of the cost metric for the at least one of the one or more quantisation parameters;
(d) adjusting the at least one of the one or more quantisation parameters based on the gradient for the at least one of the one or more quantisation parameters; and
(e) configuring the hardware to implement the DNN using the at least one of the one or more adjusted quantisation parameters by configuring the hardware to receive and process the set of values in accordance with the at least one of the one or more adjusted quantisation parameters.
Claims 1-20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-20 of US Patent No. 11,922,321. Although the claims at issue are not identical, they are not patentably distinct from each other because Claims 1-20 of US Patent No. 11,922,321 contain every element of claims 1-20 of the instant application, as detailed in the mapping table below, and as such anticipate claims 1-20 of the instant application.
“A later patent claim is not patentably distinct from an earlier patent claim if the later claim is obvious over, or anticipated by, the earlier claim. In re Longi, 759 F.2d at 896, 225 USPQ at 651 (affirming a holding of obviousness-type double patenting because the claims at issue were obvious over claims in four prior art patents); In re Berg, 140 F.3d at 1437, 46 USPQ2d at 1233 (Fed. Cir. 1998) (affirming a holding of obviousness-type double patenting where a patent application claim to a genus is anticipated by a patent claim to a species within that genus). “ELI LILLY AND COMPANY v BARR LABORATORIES, INC., United States Court of Appeals for the Federal Circuit, ON PETITION FOR REHEARING EN BANC (DECIDED: May 30, 2001).
Instant Application 18/216,461
US Patent No. 11,922,321
1. A computer-implemented method of identifying one or more quantisation parameters for transforming values to be processed by a Neural Network (NN) for implementing the NN in hardware, the method comprising, in at least one processor:
(a) determining an output of a model of the NN in response to training data, the model of the NN comprising one or more quantisation blocks, each of the one or more quantisation blocks being configured to transform one or more sets of values input to a layer of the NN to a respective fixed point number format defined by one or more quantisation parameters prior to the model processing that one or more sets of values in accordance with the layer;
(b) determining a cost metric of the NN that is a combination of an error metric and an implementation metric, the implementation metric being representative of an implementation cost of the NN based on the one or more quantisation parameters according to which the one or more sets of values have been transformed, the implementation metric being dependent on, for each of a plurality of layers of the NN:a first contribution representative of an implementation cost of an output from that layer; and a second contribution representative of an implementation cost of an output from a layer preceding that layer;
(c) back-propagating a derivative of the cost metric to at least one of the one or more quantisation parameters to generate a gradient of the cost metric for the at least one of the one or more quantisation parameters; and
(d) adjusting the at least one of the one or more quantisation parameters based on the gradient for the at least one of the one or more quantisation parameters.
1.A computer-implemented method to configure hardware to implement a Deep Neural Network (DNN), the method comprising, in at least one processor:
(a) determining an output of a model of the DNN in response to training data, the model of the DNN comprising a quantisation block configured to transform a set of values input to a layer of the DNN prior to the model processing the set of values in accordance with the layer, the transformation of the set of values simulating quantisation of the set of values to a fixed point number format defined by one or more quantisation parameters;
(b) determining an error metric for the DNN, the error metric being a quantitative measure of an error in the determined output;
(c) determining a size metric for the DNN, the size metric being proportional to a size of the DNN based on the one or more quantisation parameters;
(d) back-propagating a derivative of the error metric to at least one of the one or more quantisation parameters to generate a gradient of the error metric for the at least one of the one or more quantisation parameters;
(e) determining a gradient of the size metric for the at least one of the one or more quantisation parameters;
(f) determining a final gradient for the at least one of the one or more quantisation parameters based on the gradient of the error metric and the gradient of the size metric for the at least one of the one or more quantisation parameters; (g) adjusting the at least one of the one or more quantisation parameters based on the final gradient for the at least one of the one or more quantisation parameters; and (h) configuring the hardware to implement the DNN using the at least one of the one or more adjusted quantisation parameters by configuring the hardware to receive and process the set of values in accordance with the at least one of the one or more adjusted quantisation parameters.
Conclusion
Examiner's Note: Examiner has cited particular columns and line numbers in the references applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the teachings of the art and are applied to specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant in preparing responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner.
In the case of amending the Claimed invention, Applicant is respectfully requested to indicate the portion(s) of the specification which dictate(s) the structure relied on for proper interpretation and also to verify and ascertain the metes and bounds of the claimed invention.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KHANH B PHAM whose telephone number is (571)272-4116. The examiner can normally be reached Monday - Friday, 8am to 4pm.
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, Sanjiv Shah can be reached at (571)272-4098. 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.
/KHANH B PHAM/Primary Examiner, Art Unit 2166
February 4, 2026