Patents by Inventor Christopher Dewan

Christopher Dewan 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).

  • Systems and methods for efficiently updating neural networks
    Patent number: 10817783
    Abstract: The disclosed computer-implemented method for efficiently updating neural networks may include (i) identifying a neural network that comprises sets of interconnected nodes represented at least in part by a plurality of matrices and that is trained on a training computing device and executes on at least one endpoint device, (ii) constraining a training session for the neural network to reduce the size in memory of the difference between the previous values of the matrices prior to the training session and the new values of the matrices after the training session, (iii) creating a delta update for the neural network that describes the difference between the previous values and the new values, and (iv) updating the neural network on the endpoint device to the new state by sending the delta update from the training computing device to the endpoint computing device. Various other methods, systems, and computer-readable media are also disclosed.
    Type: Grant
    Filed: May 7, 2020
    Date of Patent: October 27, 2020
    Assignee: Facebook, Inc.
    Inventors: Nadav Rotem, Abdulkadir Utku Diril, Mikhail Smelyanskiy, Jong Soo Park, Christopher Dewan
  • Systems and methods for efficiently updating neural networks
    Patent number: 10699190
    Abstract: The disclosed computer-implemented method for efficiently updating neural networks may include (i) identifying a neural network that comprises sets of interconnected nodes represented at least in part by a plurality of matrices and that is trained on a training computing device and executes on at least one endpoint device, (ii) constraining a training session for the neural network to reduce the size in memory of the difference between the previous values of the matrices prior to the training session and the new values of the matrices after the training session, (iii) creating a delta update for the neural network that describes the difference between the previous values and the new values, and (iv) updating the neural network on the endpoint device to the new state by sending the delta update from the training computing device to the endpoint computing device. Various other methods, systems, and computer-readable media are also disclosed.
    Type: Grant
    Filed: March 4, 2018
    Date of Patent: June 30, 2020
    Assignee: Facebook, Inc.
    Inventors: Nadav Rotem, Abdulkadir Utku Diril, Mikhail Smelyanskiy, Jong Soo Park, Christopher Dewan