CTNF 18/487,802 CTNF 87556 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Double Patenting 08-33 AIA 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. 08-34 AIA Claim s 2, 4, 7, 12, 14, 15, 16, and 21 are rejected on the ground of nonstatutory double patenting as being unpatentable over claim s 1, 3, 8, 9, 11, 12, 16, and 17 of U.S. Patent No. 11,790,211 . Although the claims at issue are not identical, they are not patentably distinct from each other because the claims of the instant application are broader than the claims of US Pat. No. 11,790,211, thus granting a patent for the instant claims would unduly extend the time wise monopoly afforded to US Pat. No. 11,790,211 . 18/487,802 (Differences are highlighted in BOLD ) U.S. Patent No. 11,790,211 (Differences are highlighted in BOLD ) 2. (New) A method performed by one or more computers, the method comprising: receiving a network input for processing by a task neural network, the task neural network comprising a first partition that comprises a plurality of subnetworks, each subnetwork comprising one or more neural network layers; receiving a usage input that is different from the network input and that specifies a respective weight for each of one or more usage factors, wherein each usage factor impacts how many computational resources are used by the task neural network during the processing of the network input; and processing the network input using the task neural network in accordance with the usage input different from the network input to generate a network output for the network input, comprising: receiving an input for the first partition that is generated from the network input ; processing, using a controller neural network and conditioned on the usage input , a controller input for the first partition that comprises the input for the first partition to generate a respective score for each subnetwork of the plurality of subnetworks in the first partition ; selecting one or more subnetworks from the plurality of subnetworks in the first partition using the respective scores; and processing the input to the first partition using the one or more selected subnetworks and not any of the subnetworks that were not selected . 3. (New) The method of claim 2, wherein the controller input for the first partition comprises the usage input and the input to the first partition. 4. (New) The method of claim 2, wherein at least one subnetwork in the first partition consumes a different amount of computational resources than at least one other subnetwork in the first partition. 5. (New) The method of claim 2, wherein the neural network further comprise at least one of a base neural network layer or an output layer in addition to the first partition. 6. (New) The method of claim 2, wherein the controller neural network has been trained jointly with the task neural network. 7. (New) The method of claim 6, wherein training the controller neural network jointly with the task neural network comprises training the controller neural network and the task neural network to maximize a reward function using reinforcement learning. 8. (New) The method of claim 2, wherein the network input represents one or more of text, an utterance, an image, or a video. 9. (New) The method of claim 2, wherein each subnetwork in the first partition is configured to receive a same type of input and to generate a same type of output as each other subnetwork in the first partition. 10. (New) The method of claim 2, wherein selecting one or more subnetworks from the plurality of subnetworks in the first partition using the respective scores comprises:selecting a subnetwork from the plurality of subnetworks that has a highest score. 11. (New) The method of claim 2, wherein selecting one or more subnetworks from the plurality of subnetworks in the first partition using the respective scores comprises:selecting only one subnetwork from the plurality of subnetworks in the first partition. 12. (New) A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising: receiving a network input for processing by a task neural network, the task neural network comprising a first partition that comprises a plurality of subnetworks, each subnetwork comprising one or more neural network layers; receiving a usage input that is different from the network input and that specifies a respective weight for each of one or more usage factors, wherein each usage factor impacts how many computational resources are used by the task neural network during the processing of the network input; and processing the network input using the task neural network in accordance with the usage input different from the network input to generate a network output for the network input, comprising: receiving an input for the first partition that is generated from the network input ; processing, using a controller neural network and conditioned on the usage input, a controller input for the first partition that comprises the input for the first partition to generate a respective score for each subnetwork of the plurality of subnetworks in the first partition; selecting one or more subnetworks from the plurality of subnetworks in the first partition using the respective scores; and processing the input to the first partition using the one or more selected subnetworks and not any of the subnetworks that were not selected . 13. (New) The system of claim 12, wherein the controller input for the first partition comprises the usage input and the input to the first partition. 14. (New) The system of claim 12, wherein at least one subnetwork in the first partition consumes a different amount of computational resources than at least one other subnetwork in the first partition. 15. (New) The system of claim 12, wherein the neural network further comprise at least one of a base neural network layer or an output layer in addition to the first partition. 16. (New) The system of claim 12, wherein the controller neural network has been trained jointly with the task neural network. 17. (New) The system of claim 16, wherein training the controller neural network jointly with the task neural network comprises training the controller neural network and the task neural network to maximize a reward function using reinforcement learning. 18. (New) The system of claim 12, wherein the network input represents one or more of text, an utterance, an image, or a video. 19. (New) The system of claim 12, wherein each subnetwork in the first partition is configured to receive a same type of input and to generate a same type of output as each other subnetwork in the first partition. 20. (New) The system of claim 12, wherein selecting one or more subnetworks from the plurality of subnetworks in the first partition using the respective scores comprises:selecting only one subnetwork from the plurality of subnetworks in the first partition. 21. (New) One or more non-transitory computer storage media storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising: receiving a network input for processing by a task neural network , the task neural network comprising a first partition that comprises a plurality of subnetworks , each subnetwork comprising one or more neural network layers; receiving a usage input that is different from the network input and that specifies a respective weight for each of one or more usage factors, wherein each usage factor impacts how many computational resources are used by the task neural network during the processing of the network input; and processing the network input using the task neural network in accordance with the usage input different from the network input to generate a network output for the network input, comprising: receiving an input for the first partition that is generated from the network input ; processing, using a controller neural network and conditioned on the usage input, a controller input for the first partition that comprises the input for the first partition to generate a respective score for each subnetwork of the plurality of subnetworks in the first partition; selecting one or more subnetworks from the plurality of subnetworks in the first partition using the respective scores; and processing the input to the first partition using the one or more selected subnetworks and not any of the subnetworks that were not selected. 1. (Currently Amended) A method performed by one or more computers, the method comprising: receiving a network input for processing by a task neural network, the task neural network comprising a plurality of neural network layers; receiving a usage input that is different from the network input and that specifies a respective weight for each of one or more usage factors, wherein each usage factor impacts how many computational resources are used by the task neural network during the processing of the network input; and processing the network input using the task neural network in accordance with the usage input different from the network input to generate a network output for the network input, comprising: selecting, based at least on the usage input different from the network input, a proper subset of the plurality of neural network layers to be active while processing the network input, comprising: processing, using a trained controller neural network, a controller input that comprises the usage input different from the network input to generate a respective score for each subnetwork of a plurality of subnetworks of the task neural network in accordance with trained values of controller neural network parameters , each subnetwork comprising one or more neural network layers; and selecting a subnetwork from the plurality of subnetworks of the task neural network using the respective scores; and processing the network input using only the selected neural network layers. 3. (Original) The method of claim 2, wherein at least one subnetwork in each partition consumes a different amount of computational resources than at least one other subnetwork in the partition. 8. (Original) The method of claim 5, wherein the controller neural network has been trained jointly with the task neural network to maximize a reward function using reinforcement learning. 9. (Currently Amended) A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising: receiving a network input for processing by a task neural network, the task neural network comprising a plurality of neural network layers; receiving a usage input that is different from the network input and that specifies a respective weight for each of one or more usage factors, wherein each usage factor impacts how many computational resources are used by the task neural network during the processing of the network input; and processing the network input using the task neural network in accordance with the usage input different from the network input to generate a network output for the network input, comprising: selecting, based at least on the usage input different from the network input, a proper subset of the plurality of neural network layers to be active while processing the network input, comprising: processing , using a trained controller neural network that, a controller input that comprises the usage input different from the network input to generate a respective score for each subnetwork of a plurality of subnetworks of the task neural network in accordance with trained values of controller neural network parameters , each subnetwork comprising one or more neural network layers; and selecting a subnetwork from the plurality of subnetworks of the task neural network using the respective scores; and processing the network input using only the selected neural network layers. 11. (Original) The system of claim 10, wherein at least one subnetwork in each partition consumes a different amount of computational resources than at least one other subnetwork in the partition. 12. (Original) The system of claim 10, wherein the components further comprise at least one of a base neural network layer or an output layer in addition to the plurality of subnetworks . 16. (Original) The system of claim 13, wherein the controller neural network has been trained jointly with the task neural network to maximize a reward function using reinforcement learning . 17. (Currently Amended) One or more non-transitory computer-readable storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising: receiving a network input for processing by a task neural network, the task neural network comprising a plurality of neural network layers; receiving a usage input that is different from the network input and that specifies a respective weight for each of one or more usage factors, wherein each usage factor impacts how many computational resources are used by the task neural network during the processing of the network input; and processing the network input using the task neural network in accordance with the usage input different from the network input to generate a network output for the network input, comprising: selecting, based at least on the usage input different from the network input, a proper subset of the plurality of neural network layers to be active while processing the network input, comprising: processing, using a trained controller neural network that is conditioned on the usage input different from the network input, a controller input that comprises the usage input different from the network input to generate a respective score for each subnetwork of a plurality of subnetworks of the task neural network in accordance with trained values of controller neural network parameters, each subnetwork comprising one or more neural network layers; and selecting a subnetwork from the plurality of subnetworks of the task neural network using the respective scores; and processing the network input using only the selected neural network layers . Allowable Subject Matter Claims 2-21 are objected to in view of the double patenting rejection above, but would be allowable if a proper terminal disclaimer is submitted. Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Chen et al. (Chen) (US 2019/0073586) ([0144], the computational resources allocated to a neural network is adjusted) . Any inquiry concerning this communication or earlier communications from the examiner should be directed to JEFFERY A WILLIAMS whose telephone number is (571)270-7579. The examiner can normally be reached M-F 8:00-5:00. 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, Sath Perungavoor can be reached at 571-272-7455. 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. /JEFFERY A WILLIAMS/Primary Examiner, Art Unit 2488 Application/Control Number: 18/487,802 Page 2 Art Unit: 2488 Application/Control Number: 18/487,802 Page 3 Art Unit: 2488 Application/Control Number: 18/487,802 Page 4 Art Unit: 2488 Application/Control Number: 18/487,802 Page 5 Art Unit: 2488 Application/Control Number: 18/487,802 Page 6 Art Unit: 2488 Application/Control Number: 18/487,802 Page 7 Art Unit: 2488 Application/Control Number: 18/487,802 Page 8 Art Unit: 2488 Application/Control Number: 18/487,802 Page 9 Art Unit: 2488 Application/Control Number: 18/487,802 Page 10 Art Unit: 2488 Application/Control Number: 18/487,802 Page 11 Art Unit: 2488 Application/Control Number: 18/487,802 Page 12 Art Unit: 2488 Application/Control Number: 18/487,802 Page 13 Art Unit: 2488 Application/Control Number: 18/487,802 Page 14 Art Unit: 2488 Application/Control Number: 18/487,802 Page 15 Art Unit: 2488 Application/Control Number: 18/487,802 Page 16 Art Unit: 2488 Application/Control Number: 18/487,802 Page 17 Art Unit: 2488 Application/Control Number: 18/487,802 Page 18 Art Unit: 2488 Application/Control Number: 18/487,802 Page 19 Art Unit: 2488 Application/Control Number: 18/487,802 Page 20 Art Unit: 2488
Prosecution Insights