Patents by Inventor Nitish Srivastva

Nitish Srivastva 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).

  • SYSTEM AND METHOD FOR ADDRESSING OVERFITTING IN A NEURAL NETWORK
    Publication number: 20160335540
    Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.
    Type: Application
    Filed: July 28, 2016
    Publication date: November 17, 2016
    Inventors: Geoffrey E. Hinton, Alexander Krizhevsky, Ilya Sutskever, Nitish Srivastva
  • System and method for addressing overfitting in a neural network
    Patent number: 9406017
    Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.
    Type: Grant
    Filed: August 30, 2013
    Date of Patent: August 2, 2016
    Assignee: Google Inc.
    Inventors: Geoffrey E. Hinton, Alexander Krizhevsky, Ilya Sutskever, Nitish Srivastva
  • SYSTEM AND METHOD FOR ADDRESSING OVERFITTING IN A NEURAL NETWORK
    Publication number: 20140180986
    Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.
    Type: Application
    Filed: August 30, 2013
    Publication date: June 26, 2014
    Applicant: Google Inc.
    Inventors: Geoffrey E. Hinton, Alexander Krizhevsky, Ilya Sutskever, Nitish Srivastva