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 .
The following action is in response to the amendment and remarks of 03/02/2026.
By the amendment, claims 1, 3, 5, 8-9 and 11-13 are amended; claims 2, 4 and 10 are canceled.
Claims 1, 3, 5-9 and 11-13 are pending and have been considered below.
Response to Amendment/Arguments
The specification objection has been withdrawn in light of the specification amendment and corresponding remarks.
The drawing objection has been maintained in light of the replacement sheet drawing amendment and corresponding remarks; element 304 of Fig. 3 remains blurry and unclear.
The 35 USC 112(b) rejection of claims 2 and 5 has been withdrawn in light of the claims amendment and corresponding remarks.
The 35 USC 101 rejection of claims 1-13 has been withdrawn in light of the claims amendment and corresponding remarks.
Applicant argues, regarding the 35 USC 102 rejection of claims 1-13 by BRADY, that BRADY fails to teach or suggest pre-defined points of intersection which are provided in a configuration file; particularly that the sub-models of BRADY are chosen by the internal compiler algorithm with no disclosure of pre-defined points or pre-defined points in a configuration file and instead BRADY shows only a target descriptor file that states hardware characteristics of a target computing device. The Examiner respectfully disagrees.
BRADY discloses dividing the intermediate representation into sub-models using logic to provide distinct configurable representations of the underlying mathematical structure (¶52: “A set of sub-models (e.g., 1005, 1010, 1015) may be generated and encapsulated within the intermediate representation 140 to provide a configurable representation of a mathematical structure (e.g., the computation model of the intermediate representation) of the neural network described in graph 110, for instance, in the form of one or more computation graphs from which a binary may be constructed, among other example implementations. The sub-models may each provide distinct views, but refer to the same underlying structure, the computation model of the intermediate representation. This may allow the overall complexity of the intermediate representation to be simplified to address compilation issues in isolation while sustaining the coherence of the logical space, which allows efficient processing of mutual relations between all types of entities considered.”). Broadly, this anticipates “dissecting the first intermediate artificial neural network graph at pre-defined points of intersection” as the points of intersection of the claim do not preclude this interpretation; the argument is not persuasive.
Further BRADY discloses that at least some of the sub-models are defined using the target descriptor file (¶85: “Using the target descriptor, resource sub-models may be defined within intermediate representations generated by the compiler for various neural network models as part of the initialization of the compilation process.”). BRADY also discloses wherein a neural network binary file is parsed to generate the particular sub-models that divide the intermediate representation (¶98: “Continuing with the example illustrated by flowchart 1500, composing an intermediate representation of the DNN may include (at 1522) parsing a neural network binary file (e.g., implemented as a graph data structure) at the compiler and composing an internal representation of the network with a direct translation of one operator to one or more nodes to generate sub-models of the intermediate representation. In some implementations, the sub-models may include an operator sub-model, a data sub-model, and a control sub-model, such as discussed herein.”). Broadly, this anticipates “generate a plurality of second intermediate artificial neural network graphs based on a specification file” and “the pre-defined points of intersection being provided in a configuration file” as the claim does merely requires the generation “based on” a specification file and the points being “provided in” a configuration file; the argument is not persuasive.
The 35 USC 102 rejection of claims 1-13 by BRADY has been updated and maintained in light of the amendment and corresponding remarks; the updated rejection of claims 1, 3, 5-9 and 11-13 under 35 USC 102 by BRADY is found below.
Drawings
The drawings are objected to for containing blurry or unclear features (See Fig. 3 304). Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
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, 3, 5-9 and 11-13 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Brady et al., US 2019/0391796 A1 [“BRADY”].
Regarding claim 1, BRADY discloses a computer implemented method for adapting an artificial neural network graph (Fig. 2, ¶26), the method comprising:
acquiring an input artificial neural network graph (¶51: inputting neural network graph 110, Fig. 10);
carrying out a global manipulation step comprising a first set of manipulations configured to adapt the input artificial neural network graph based on at least one user-defined criterion and generate a first intermediate artificial neural network graph (¶51-52: generating an intermediate representation from the input graph and the target descriptor file, ¶69-70: file is authored by one or more users, ¶85);
dissecting the first intermediate artificial neural network graph at pre-defined points of intersection (¶52: dividing the intermediate representation into sub-models along logical points corresponding to representations of the mathematical structure, ¶98) to generate a plurality of second intermediate artificial neural network graphs based on a specification file (¶52: generate a set of sub-models within the intermediate representation representing distinct logical views of the computational model of the intermediate representation, ¶85: sub-models may be defined using a target descriptor file), the pre-defined points of intersection being provided in a configuration file (¶98: parsing a binary file to generate sub-models); and
carrying out a respective local manipulation step for each of the plurality of second intermediate artificial neural network graphs, wherein each local manipulation step comprises a corresponding second set of manipulations configured to adapt a corresponding second intermediate artificial neural network graph based on at least one corresponding user-defined criterion, to generate a plurality of manipulated second intermediate artificial neural network graphs corresponding to the plurality of second intermediate artificial neural networks (¶93-94: inserting barrier task barrier task objects into sub-models, ¶53: barrier tasks generated from target hardware barrier information of the target descriptor file, ¶104: each compilation pass based on target descriptor may transform the intermediate representation sub-model graphs);
converting each of the plurality of manipulated second intermediate artificial neural network graphs to an on-board format that is directly executable on a resource-constrained embedded system (¶50: produce a binary executable for target hardware, ¶57, ¶97: transformed neural network used to generate binary file for execution by the target device, ¶104);
deploying at least one of the plurality of manipulated second intermediate artificial neural network graphs, converted into the on-board format, on the resource-constrained embedded system (¶57: runtime software executes the binary executable including the hardware barrier control flow, ¶97)
Regarding claim 3, BRADY discloses the computer implemented method of at least one of claim 1, wherein the first set of manipulations and/or the second set of manipulations are provided in the configuration file (¶77).
Regarding claim 5, BRADY discloses the computer implemented method of at least one of claim 4, wherein the configuration file is a textual configuration file (¶51-52, ¶77: target descriptor file, ex. JSON file readable/editable).
Regarding claim 6, BRADY discloses the computer implemented method of at least one of claim 1, wherein the input artificial neural network graph is provided in an off-board format (¶26: graph definition of neural network).
Regarding claim 7, BRADY discloses the computer implemented method of at least one of claim 1, wherein carrying out the respective local manipulation step comprises carrying out individual manipulations to at least two second intermediate artificial neural network graphs (¶93-94: operator and control models).
Regarding claim 8, BRADY discloses the computer implemented method of at least one of claim 1, wherein each of the input artificial neural network graph, the first intermediate artificial neural network graph, the plurality of second intermediate artificial neural network graphs, and the at least one of the plurality of manipulated second intermediate artificial neural network graphs comprises a respective plurality of nodes representing mathematical operations and a respective plurality of edges representing tensors (¶52: computation model, sub-models of same underlying structure, ¶60: nodes/edges representing tensors).
Regarding claim 9, BRADY discloses the computer implemented method of at least one of claim 1, further comprising:
visualizing at least one graph selected from a list of graphs consisting of: the input artificial neural network graph, the first intermediate artificial neural network graph, the plurality of second intermediate artificial neural network graphs, and the at least one of the plurality of manipulated second intermediate artificial neural network graphs (¶72: rendering output data of the graph).
Regarding claim 11, BRADY discloses the computer implemented method of claim 10, wherein the resource-constrained embedded system is a one of a mobile computing device, a mobile phone, a tablet computing device, an automotive compute platform, or an edge device (¶33).
Regarding claim 12, BRADY discloses a computer system, the computer system storing computer executable instructions for carrying out the computer implemented method of at least one of claim 1 (claim 19).
Regarding claim 13, BRADY discloses a non-transitory computer readable medium comprising instructions for carrying out the computer implemented method of at least one of claim 1 (claim 1).
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
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 ANDREW L TANK whose telephone number is (571)270-1692. The examiner can normally be reached Monday-Thursday 9a-6p.
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, Matthew Ell can be reached at 571-270-3264. 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 L TANK/Primary Examiner, Art Unit 2141
Prosecution Insights