Patents by Inventor Bhavin V. Nayak

Bhavin V. Nayak has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11880763
    Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.
    Type: Grant
    Filed: May 28, 2020
    Date of Patent: January 23, 2024
    Assignee: Intel Corporation
    Inventors: Furkan Isikdogan, Bhavin V. Nayak, Joao Peralta Moreira, Chyuan-Tyng Wu, Gilad Michael
  • Patent number: 11868892
    Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.
    Type: Grant
    Filed: August 12, 2022
    Date of Patent: January 9, 2024
    Assignee: INTEL CORPORATION
    Inventors: Furkan Isikdogan, Bhavin V. Nayak, Joao Peralta Moreira, Chyuan-Tyng Wu, Gilad Michael
  • Publication number: 20220391680
    Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.
    Type: Application
    Filed: August 12, 2022
    Publication date: December 8, 2022
    Inventors: Furkan Isikdogan, Bhavin V. Nayak, Joao Peralta Moreira, Chyuan-Tyng Wu, Gilad Michael
  • Publication number: 20200293870
    Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.
    Type: Application
    Filed: May 28, 2020
    Publication date: September 17, 2020
    Applicant: Intel Corporation
    Inventors: Furkan Isikdogan, Bhavin V. Nayak, Joao Peralta Moreira, Chyuan-Tyng Wu, Gilad Michael