Patents by Inventor Sunil Bopardikar

Sunil Bopardikar 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).

  • Reducing the size of a neural network through reduction of the weight matrices
    Patent number: 11030522
    Abstract: Systems and methods for reducing the size of neural networks are disclosed. In an embodiment, a server computer stores a plurality of training datasets, each of which comprise a plurality of training input matrices and a plurality of corresponding outputs. The server computer initiates training of a neural network using the plurality of training input matrices, a weight matrix, and the plurality of corresponding outputs. While the training of the neural network is being performed, the server computer identifies one or more weight values of the weight matrix for removal. The server computer removes the one or more weight values from the weight matrix to generate a reduced weight matrix. The server computer then stores the reduced weight matrix with the neural network.
    Type: Grant
    Filed: October 18, 2018
    Date of Patent: June 8, 2021
    Inventors: Rohan Bopardikar, Sunil Bopardikar
  • REDUCING THE SIZE OF A NEURAL NETWORK THROUGH REDUCTION OF THE WEIGHT MATRICES
    Publication number: 20190050733
    Abstract: Systems and methods for reducing the size of neural networks are disclosed. In an embodiment, a server computer stores a plurality of training datasets, each of which comprise a plurality of training input matrices and a plurality of corresponding outputs. The server computer initiates training of a neural network using the plurality of training input matrices, a weight matrix, and the plurality of corresponding outputs. While the training of the neural network is being performed, the server computer identifies one or more weight values of the weight matrix for removal. The server computer removes the one or more weight values from the weight matrix to generate a reduced weight matrix. The server computer then stores the reduced weight matrix with the neural network.
    Type: Application
    Filed: October 18, 2018
    Publication date: February 14, 2019
    Inventors: ROHAN BOPARDIKAR, SUNIL BOPARDIKAR
  • Reducing the size of a neural network through reduction of the weight matrices
    Patent number: 10127495
    Abstract: Systems and methods for reducing the size of deep neural networks are disclosed. In an embodiment, a server computer stores a plurality of training datasets, each of which comprise a plurality of training input matrices and a plurality of corresponding outputs. The server computer initiates training of a deep neural network using the plurality of training input matrices, a weight matrix, and the plurality of corresponding outputs. While the training of the deep neural network is being performed, the server computer identifies one or more weight values of the weight matrix for removal. The server computer removes the one or more weight values from the weight matrix to generate a reduced weight matrix. The server computer then stores the reduced weight matrix with the deep neural network.
    Type: Grant
    Filed: April 14, 2017
    Date of Patent: November 13, 2018
    Inventors: Rohan Bopardikar, Sunil Bopardikar