DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . This action is responsive to the Application filed on 05/04/2023. Claims 1-20 are pending in the case. Claims 1, 8, and 15 are independent claims.
Claim Rejections - 35 U.S.C. § 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 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 of this title, 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.
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 are advised of the obligation under 37 C.F.R. § 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.
Claims 1-4, 7-11, and 14-18 are rejected under 35 U.S.C. § 103 as being unpatentable over Chen et al. (Chen, Mingcai, Yuntao Du, Yi Zhang, Shuwei Qian, and Chongjun Wang. "Semi-supervised learning with multi-head co-training." In Proceedings of the AAAI conference on artificial intelligence, vol. 36, no. 6, pp. 6278-6286. 2022, hereinafter Chen) in view of Ding et al. (Ding, Xiaohan, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, and Jian Sun. "Repvgg: Making vgg-style convnets great again." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 13733-13742. 2021., hereinafter Ding).
As to independent claims 1, 8, and 15, Chen teaches:
An apparatus to re-parameterize multiple head networks of an artificial intelligence (AI) model, the apparatus comprising: interface circuitry; machine readable instructions; and programmable circuitry to at least one of instantiate or execute the machine readable instructions to (Title and abstract):
train an Al model using labeled data and pseudo-labeled data, the Al model including multiple head networks (Page 6280, "SSL aims to model a class distribution p(y | x) for input x utilizing both labeled and unlabeled data". Page 6280, "For co-training, every head interacts with its peers through pseudo-labels on unlabeled data". Page 6280, figure 1, shared module and classification heads. Page 6280, section entitled "Muti-Head Co-Training"); and
after the Al model has been trained,… the multiple head networks of the Al model… without re-parameterizing other portions of the Al model (Page 6281, "During test-time, we simply ensemble all heads’ predictions of the EMA model by adding them together". Figure 1, shared module separate from the classification heads).
Chen does not appear to expressly teach re-parameterize… networks of the Al model into a fully connected layer without re-parameterizing other portions of the Al model.
Ding teaches re-parameterize… networks of the Al model into a fully connected layer without re-parameterizing other portions of the Al model (Page 13774, "use structural re-parameterization to decouple a training-time multi-branch topology with an inference-time plain architecture").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the multi-head co-training of Chen to include the re-parameterization techniques of Ding to improve accuracy and speed (see Ding at abstract).
As to dependent claims 2, 9, and 16, Chen further teaches generate, with the Al model, the pseudo-labeled data by classifying unlabeled data with the multiple head networks (Page 6280, "For co-training, every head interacts with its peers through pseudo-labels on unlabeled data. To obtain reliable predictions for pseudo-labeling, weakly augmented unlabeled examples ^ub = Augw(ub) first pass through the shared module and all heads simultaneously,").
As to dependent claims 3, 10, and 17, Chen further teaches multiple head networks (Page 6281, "During test-time, we simply ensemble all heads’ predictions of the EMA model by adding them together". Figure 1, shared module separate from the classification heads).
Chen does not appear to expressly teach re-parameterize the multiple head networks into multiple fully connected layers; and re-parameterize the multiple fully connected layers and an average operator into the fully connected layer.
Ding teaches re-parameterize the multiple head networks into multiple fully connected layers; and re-parameterize the multiple fully connected layers and an average operator into the fully connected layer (Page 13774, "use structural re-parameterization to decouple a training-time multi-branch topology with an inference-time plain architecture").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the multi-head co-training of Chen to include the re-parameterization techniques of Ding to improve accuracy and speed (see Ding at abstract).
As to dependent claims 4, 11, and 18, Chen further teaches the fully connected layer is a first fully connected layer (Page 6283, "one fully connected layer and the shared module has the structure of one convolutional layer and two blocks"); the multiple head networks and the multiple non-linear layers (Page 6280, figure 1, shared module and classification heads).
Chen does not appear to expressly teach respective head networks of the multiple head networks include…, an identity layer, an average operator, and a second fully connected layer; and respective non-linear layers… include a third fully connected layer and a batch normalization layer.
Ding teaches respective head networks of the multiple head networks include…, an identity layer, an average operator, and a second fully connected layer; and respective non-linear layers… include a third fully connected layer and a batch normalization layer (Figure 2, identity branches. Page 13737, "global average pooling followed by a fully-connected layer as the head". Page 13737, "the BN layer").
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the multi-head co-training of Chen to include the re-parameterization techniques of Ding to improve accuracy and speed (see Ding at abstract).
As to dependent claims 7 and 14, Chen further teaches determine whether the Al model has been trained for a threshold number of epochs (Page 6281, "The algorithm proceeds until reaching fixed iterations").
Allowable Subject Matter
Claims 5, 6, 12, 13, 19, and 20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Citation of Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Ding et al. (Ding, Xiaohan, Xiangyu Zhang, Jungong Han, and Guiguang Ding. "Diverse branch block: Building a convolution as an inception-like unit." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 10886-10895. 2021) teaches a universal building block of Convolutional Neural Network (ConvNet) to improve the performance without any inference-time costs. The block is named Diverse Branch Block (DBB), which enhances the representational capacity of a single convolution by combining diverse branches of different scales and complexities to enrich the feature space, including sequences of convolutions, multi-scale convolutions, and average pooling. After training, a DBB can be equivalently converted into a single conv layer for deployment. Unlike the advancements of novel ConvNet architectures, DBB complicates the training-time microstructure while maintaining the macro architecture, so that it can be used as a drop-in replacement for regular conv layers of any architecture. In this way, the model can be trained to reach a higher level of performance and then transformed into the original inference-time structure for inference. DBB improves ConvNets on image classification (up to 1.9% higher top-1 accuracy on ImageNet), object detection and semantic segmentation.
Conclusion
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure. Applicant is required under 37 C.F.R. § 1.111(c) to consider these references fully when responding to this action.
It is noted that any citation to specific pages, columns, lines, or figures in the prior art references and any interpretation of the references should not be considered to be limiting in any way. A reference is relevant for all it contains and may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art. In re Heck, 699 F.2d 1331, 1332-33, 216 U.S.P.Q. 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1009, 158 U.S.P.Q. 275, 277 (C.C.P.A. 1968)).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Casey R. Garner whose telephone number is 571-272-2467. The examiner can normally be reached Monday to Friday, 8am to 5pm, Eastern Time.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Alexey Shmatov can be reached on 571-270-3428. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center and Private PAIR to authorized users only. Should you have questions about access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
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) Form at https://www.uspto.gov/patents/uspto-automated- interview-request-air-form.
/Casey R. Garner/Primary Examiner, Art Unit 2123
Prosecution Insights