Patents by Inventor Hanie Sedghi

Hanie Sedghi 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).

  • Regularizing the training of convolutional neural networks
    Patent number: 11409991
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a convolutional neural network using a regularization scheme. One of the methods includes repeatedly performing the following operations: obtaining a kernel of a particular convolutional layer; applying a Fourier transform to the kernel; generating a decomposition using singular-value decomposition (SVD); generating a regularized diagonal matrix; generating a recomposition; applying an inverse Fourier transform to the recomposition; and training the convolutional neural network on training inputs.
    Type: Grant
    Filed: May 24, 2019
    Date of Patent: August 9, 2022
    Assignee: Google LLC
    Inventors: Vineet Gupta, Philip M. Long, Hanie Sedghi
  • REGULARIZING THE TRAINING OF CONVOLUTIONAL NEURAL NETWORKS
    Publication number: 20200372300
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a convolutional neural network using a regularization scheme. One of the methods includes repeatedly performing the following operations: obtaining a kernel of a particular convolutional layer; applying a Fourier transform to the kernel; generating a decomposition using singular-value decomposition (SVD); generating a regularized diagonal matrix; generating a recomposition; applying an inverse Fourier transform to the recomposition; and training the convolutional neural network on training inputs.
    Type: Application
    Filed: May 24, 2019
    Publication date: November 26, 2020
    Inventors: Vineet Gupta, Philip M. Long, Hanie Sedghi