Patents by Inventor Vishwesh Nath

Vishwesh Nath 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).

  • ACTIVE LEARNING WITH ANNOTATION SCORES
    Publication number: 20250061323
    Abstract: Apparatuses, systems, and techniques to perform active learning.
    Type: Application
    Filed: September 12, 2023
    Publication date: February 20, 2025
    Inventors: Vishwesh Nath, Daguang Xu, Bin Liu, Yufan He, Sachidanand Alle, Pengcheng Ma, Raghav Mani, Marc Thomas Edgar, Andrew Feng
  • FEDERATED LEARNING TECHNIQUE
    Publication number: 20240303504
    Abstract: Apparatuses, systems, and techniques to train/use one or more neural networks. In at least one embodiment, a processor comprises one or more circuits to cause neural network training information to be aggregated based, at least in part, on contribution of the neural network training data and one or more performance metrics of the neural network.
    Type: Application
    Filed: March 22, 2023
    Publication date: September 12, 2024
    Inventors: Ziyue Xu, Holger Reinhard Roth, Meirui Jiang, Wenqi Li, Dong Yang, Can Zhao, Vishwesh Nath, Daguang Xu
  • PREPROCESSING DATA USING A NETWORK INTERFACE
    Publication number: 20240185100
    Abstract: Methods and systems for obtaining data having a first format, converting the data to a second format, storing the converted data in memory accessible by at least one parallel processing unit, and processing the converted data stored in the memory using the at least one parallel processing unit.
    Type: Application
    Filed: December 6, 2022
    Publication date: June 6, 2024
    Inventors: Alvin Ihsani, Shaul Arazi, Elena Agostini, Penn Tasinga, Carl Everett Lacey, JR., Dana Groff, Dotan David Levi, Wojciech Wasko, Vishwesh Nath, Sachidanand Alle
  • GENERATING NEURAL NETWORKS
    Publication number: 20240169180
    Abstract: Apparatuses, systems, and techniques to generate one or more neural networks. In at least one embodiment, one or more neural networks are generated, based on, for example, one or more convolutional neural network operations and one or more transformer neural network operations.
    Type: Application
    Filed: November 18, 2022
    Publication date: May 23, 2024
    Inventors: Dong Yang, Yufan He, Ziyue Xu, Ali Hatamizadeh, Vishwesh Nath, Wenqi Li, Andriy Myronenko, Can Zhao, Holger Reinhard Roth, Daguang Xu
  • NEURAL NETWORK ARCHITECTURE SELECTION
    Publication number: 20240104345
    Abstract: Apparatuses, systems, and techniques are presented to generate images representing realistic motion or activity. In at least one embodiment, one or more neural networks are used to select a first neural network to perform a first task based, at least in part, upon a performance estimated by a second neural network.
    Type: Application
    Filed: July 7, 2022
    Publication date: March 28, 2024
    Inventors: Cheng Peng, Andriy Myronenko, Ali Hatamizsadeh, Vishwesh Nath, Md Mahfuzur Rahman Siddiquee, Yufan He, Daguang Xu, Dong Yang
  • VOLUMETRIC IMAGE ANNOTATION USING ONE OR MORE NEURAL NETWORKS
    Publication number: 20230036451
    Abstract: Apparatuses, systems, and techniques are presented to predict annotations for objects in images. In at least one embodiment, one or more neural networks are used to help generate one or more segmentation boundaries of one or more objects within one or more digital images, wherein the one or more neural networks are to transform one or more representations of one or more portions of the one or more objects into one or more lower-dimensional representations of the one or more portions of the one or more objects.
    Type: Application
    Filed: July 13, 2021
    Publication date: February 2, 2023
    Inventors: Ali Hatamizadeh, Daguang Xu, Dong Yang, Holger Reinhard Roth, Andriy Myronenko, Vishwesh Nath, Yucheng Tang
  • IMAGE ANNOTATION USING ONE OR MORE NEURAL NETWORKS
    Publication number: 20210334955
    Abstract: Apparatuses, systems, and techniques are presented to predict annotations for objects in images. In at least one embodiment, one or more annotations corresponding to one or more objects within one or more images are generated based, at least in part, on one or more neural networks iteratively trained using the one or more images.
    Type: Application
    Filed: April 24, 2020
    Publication date: October 28, 2021
    Inventors: Holger Roth, Dong Yang, Daguang Xu, Vishwesh Nath