Patents by Inventor Guruprasad Raghavan

Guruprasad Raghavan 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).

  • FLEXIBLE MACHINE LEARNING
    Publication number: 20220391673
    Abstract: Disclosed herein include systems, devices, and methods for flexible machine learning by traversing functionally invariant paths in weight space.
    Type: Application
    Filed: May 27, 2022
    Publication date: December 8, 2022
    Inventors: Matthew W. Thomson, Guruprasad Raghavan
  • RESILIENCE DETERMINATION AND DAMAGE RECOVERY IN NEURAL NETWORKS
    Publication number: 20210397964
    Abstract: Disclosed herein include systems, devices, computer readable media, and methods for resilience determination and damage recovery in neural networks using a weight space and a metric that together form a manifold (such as a pseudo-Riemannian manifold or a Riemannian manifold)
    Type: Application
    Filed: June 16, 2021
    Publication date: December 23, 2021
    Inventors: Guruprasad Raghavan, Matthew W. Thomson
  • SELF ORGANIZATION OF NEUROMORPHIC MACHINE LEARNING ARCHITECTURES
    Publication number: 20210224633
    Abstract: Disclosed herein include systems, methods, devices, and computer readable media for constructing a neural network by growing and self-organizing.
    Type: Application
    Filed: December 18, 2020
    Publication date: July 22, 2021
    Inventors: Guruprasad Raghavan, Matthew W. Thomson, Cong Lin