Patents by Inventor Ronak R. Mehta

Ronak R. Mehta 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).

  • Dual flow generative computer architecture
    Patent number: 11544607
    Abstract: A machine learning architecture employs two machine learning networks that are joined by a statistical model allowing the imposition of a predetermined statistical model family into a learning process in which the networks translate between and data types. For example, the statistical model may enforce a Gaussian conditional probability between the latent variables in the translation process. In one application, MRI images may be translated into PET images with reduced mode collapse, blurring, or other “averaging” type behaviors.
    Type: Grant
    Filed: May 20, 2019
    Date of Patent: January 3, 2023
    Assignee: Wisconsin Alumni Research Foundation
    Inventors: Haoliang Sun, Ronak R. Mehta, Hao Zhou, Vikas Singh, Vivek Prabhakaran, Stirling C. Johnson
  • Neural network architecture with concurrent uncertainty output
    Patent number: 11537846
    Abstract: A neural net processor provides twin processing paths trainable using different moments of the input data, one moment providing a proxy for uncertainty. Subsequent operation of the trained neural net allows monitoring of the uncertainty proxy to provide real-time assessment of neural net model-based uncertainty.
    Type: Grant
    Filed: August 21, 2018
    Date of Patent: December 27, 2022
    Assignee: Wisconsin Alumni Research Foundation
    Inventors: Seong Jae Hwang, Ronak R. Mehta, Vikas Singh
  • Dual Flow Generative Computer Architecture
    Publication number: 20200372384
    Abstract: A machine learning architecture employs two machine learning networks that are joined by a statistical model allowing the imposition of a predetermined statistical model family into a learning process in which the networks translate between and data types. For example, the statistical model may enforce a Gaussian conditional probability between the latent variables in the translation process. In one application, MRI images may be translated into PET images with reduced mode collapse, blurring, or other “averaging” type behaviors.
    Type: Application
    Filed: May 20, 2019
    Publication date: November 26, 2020
    Inventors: Haoliang Sun, Ronak R. Mehta, Hao Zhou, Vikas Singh, Vivek Prabhakaran, Stirling C. Johnson
  • Neural Network Architecture with Concurrent Uncertainty Output
    Publication number: 20200065648
    Abstract: A neural net processor provides twin processing paths trainable using different moments of the input data, one moment providing a proxy for uncertainty. Subsequent operation of the trained neural net allows monitoring of the uncertainty proxy to provide real-time assessment of neural net model-based uncertainty.
    Type: Application
    Filed: August 21, 2018
    Publication date: February 27, 2020
    Inventors: Seong Jae Hwang, Ronak R. Mehta, Vikas Singh