Patents by Inventor Marc Teva Law

Marc Teva Law 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).

  • Publication number: 20250111201
    Abstract: Embodiments are disclosed for a generating graph representations of neural networks to be used as input for one or more metanetworks. Architectural information can be extracted from a neural network and used to generate graph a representation. A subgraph can be generated for each layer of the neural network, where each subgraph includes nodes that correspond to neurons and connecting edges that correspond to weights. Each layer of the neural network can be associated with a bias node that is connected to individual nodes of that layer using edges representing bias weights. Various types of neural networks and layers of neural networks can be represented by such graphs, which are then used as inputs for metanetworks. The subgraphs can be combined into a comprehensive graph representation of the neural network, which can be provided as input to a metanetwork to generate network parameters or perform another such operation.
    Type: Application
    Filed: September 28, 2023
    Publication date: April 3, 2025
    Inventors: James Robert Lucas, Derek Lim, Haggai Maron, Marc Teva Law
  • Publication number: 20240320993
    Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
    Type: Application
    Filed: May 24, 2024
    Publication date: September 26, 2024
    Inventors: Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche, Eric Cameracci, Gavriel State, Marc Teva Law
  • Patent number: 11995883
    Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
    Type: Grant
    Filed: February 2, 2023
    Date of Patent: May 28, 2024
    Assignee: Nvidia Corporation
    Inventors: Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche, Eric Cameracci, Gavriel State, Marc Teva Law
  • Publication number: 20240126811
    Abstract: Apparatuses, systems, and techniques to indicate data dependencies. In at least one embodiment, one or more neural networks are used to generate one or more indicators of one or more data dependencies and one or more indicators of direction of the one or more data dependencies.
    Type: Application
    Filed: January 17, 2023
    Publication date: April 18, 2024
    Inventors: Marc Teva Law, James Robert Lucas
  • Publication number: 20230177826
    Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
    Type: Application
    Filed: February 2, 2023
    Publication date: June 8, 2023
    Inventors: Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche, Eric Cameracci, Gavriel State, Marc Teva Law
  • Patent number: 11574155
    Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
    Type: Grant
    Filed: April 9, 2021
    Date of Patent: February 7, 2023
    Assignee: Nvidia Corporation
    Inventors: Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche, Eric Cameracci, Gavriel State, Marc Teva Law
  • Publication number: 20210374489
    Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.
    Type: Application
    Filed: April 9, 2021
    Publication date: December 2, 2021
    Inventors: Aayush Prakash, Shoubhik Debnath, Jean-Francois Lafleche, Eric Cameracci, Gavriel State, Marc Teva Law