Patents by Inventor Jason T. Jones

Jason T. Jones 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).

  • Methods and apparatus for matrix processing in a convolutional neural network
    Patent number: 12333405
    Abstract: Described examples include an integrated circuit including a vector multiply unit including a plurality of multiply/accumulate nodes, in which the vector multiply unit is operable to provide an output from the multiply/accumulate nodes, a first data feeder operable to provide first data to the vector multiply unit in vector format, and a second data feeder operable to provide second data to the vector multiply unit in vector format.
    Type: Grant
    Filed: September 29, 2020
    Date of Patent: June 17, 2025
    Assignee: TEXAS INSTRUMENTS INCORPORATED
    Inventors: Mihir Narendra Mody, Shyam Jagannathan, Manu Mathew, Jason T. Jones
  • METHODS AND APPARATUS FOR MATRIX PROCESSING IN A CONVOLUTIONAL NEURAL NETWORK
    Publication number: 20220101083
    Abstract: Described examples include an integrated circuit including a vector multiply unit including a plurality of multiply/accumulate nodes, in which the vector multiply unit is operable to provide an output from the multiply/accumulate nodes, a first data feeder operable to provide first data to the vector multiply unit in vector format, and a second data feeder operable to provide second data to the vector multiply unit in vector format.
    Type: Application
    Filed: September 29, 2020
    Publication date: March 31, 2022
    Inventors: Mihir Narendra Mody, Shyam Jagannathan, Manu Mathew, Jason T. Jones
  • Methods and apparatus for matrix processing in a convolutional neural network
    Patent number: 10824934
    Abstract: Described examples include an integrated circuit including a vector multiply unit including a plurality of multiply/accumulate nodes, in which the vector multiply unit is operable to provide an output from the multiply/accumulate nodes, a first data feeder operable to provide first data to the vector multiply unit in vector format, and a second data feeder operable to provide second data to the vector multiply unit in vector format.
    Type: Grant
    Filed: October 16, 2017
    Date of Patent: November 3, 2020
    Assignee: TEXAS INSTRUMENTS INCORPORATED
    Inventors: Mihir Narendra Mody, Shyam Jagannathan, Manu Mathew, Jason T. Jones
  • METHODS AND APPARATUS FOR MATRIX PROCESSING IN A CONVOLUTIONAL NEURAL NETWORK
    Publication number: 20180197067
    Abstract: Described examples include an integrated circuit including a vector multiply unit including a plurality of multiply/accumulate nodes, in which the vector multiply unit is operable to provide an output from the multiply/accumulate nodes, a first data feeder operable to provide first data to the vector multiply unit in vector format, and a second data feeder operable to provide second data to the vector multiply unit in vector format.
    Type: Application
    Filed: October 16, 2017
    Publication date: July 12, 2018
    Inventors: Mihir Narendra Mody, Shyam Jagannathan, Manu Mathew, Jason T. Jones