Patents by Inventor Priya L. Donti

Priya L. Donti 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).

  • Neural network with a layer solving a semidefinite program
    Patent number: 11748627
    Abstract: A system for applying a neural network to an input instance. The neural network includes an optimization layer for determining values of one or more output neurons from values of one or more input neurons by a joint optimization parametrized by one or more parameters. An input instance is obtained. The values of the one or more input neurons to the optimization layer are obtained and input vectors for the one or more input neurons are determined therefrom. Output vectors for the one or more output neurons are computed from the determined input vectors by jointly optimizing at least the output vectors with respect to the input vectors to solve a semidefinite program defined by the one or more parameters. The values of the one or more output neurons are determined from the respective computed output vectors.
    Type: Grant
    Filed: May 12, 2020
    Date of Patent: September 5, 2023
    Assignees: ROBERT BOSCH GMBH, CARNEGIE MELLON UNIVERSITY
    Inventors: Csaba Domokos, Jeremy Zieg Kolter, Po-Wei Wang, Priya L. Donti
  • CONTROLLER WITH NEURAL NETWORK AND IMPROVED STABILITY
    Publication number: 20210302921
    Abstract: A controller for generating a control signal for a computer-controlled machine. A neural network may be applied to a current sensor signal, the neural network being configured to map the sensor signal to a raw control signal. A projection function may be applied to the raw control signal to obtain a stable control signal to control the computer-controllable machine.
    Type: Application
    Filed: February 25, 2021
    Publication date: September 30, 2021
    Inventors: Jeremy Zieg Kolter, Melrose Roderick, Priya L. Donti, Julia Vinogradska
  • NEURAL NETWORK WITH A LAYER SOLVING A SEMIDEFINITE PROGRAM
    Publication number: 20200372364
    Abstract: A system for applying a neural network to an input instance. The neural network includes an optimization layer for determining values of one or more output neurons from values of one or more input neurons by a joint optimization parametrized by one or more parameters. An input instance is obtained. The values of the one or more input neurons to the optimization layer are obtained and input vectors for the one or more input neurons are determined therefrom. Output vectors for the one or more output neurons are computed from the determined input vectors by jointly optimizing at least the output vectors with respect to the input vectors to solve a semidefinite program defined by the one or more parameters. The values of the one or more output neurons are determined from the respective computed output vectors.
    Type: Application
    Filed: May 12, 2020
    Publication date: November 26, 2020
    Inventors: Csaba Domokos, Jeremy Zieg Kolter, Po-wei Wang, Priya L. Donti