Patents by Inventor David J. Freedman

David J. Freedman 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).

  • Publication number: 20240160944
    Abstract: A method includes selecting artificial neural network parameters; sampling the parameters; selecting connection weights; initializing the artificial neural networks; running the artificial neural networks on cognitive tasks; and determining whether activity is within an acceptable range. A computing system includes a processor; and a memory having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to select artificial neural network parameters; sample the parameters; select connection weights; initialize the artificial neural networks; run the artificial neural networks on cognitive tasks; and determine whether activity is within an acceptable range.
    Type: Application
    Filed: April 21, 2023
    Publication date: May 16, 2024
    Inventors: Nicolas Y. Masse, David J. Freedman, Matthew C. Rosen
  • Publication number: 20220067442
    Abstract: A computing device may receive a first set of training data for training an ANN to predict output data for a first task, and may train the ANN with the first set of training data by only adjusting values of weights associated with a first subset of neurons, the first subset selected based on an identity of the first task. The computing device may receive a second, different set of training data for training the ANN to predict output data for a second task, and may train the ANN with the second set of training data by only adjusting values of weights associated with a second subset of neurons, the second subset selected based on an identity of the second task. During training, adjusting of the value of any weight may entail weight stabilization that depends on whether there has been any training for one or more previous tasks.
    Type: Application
    Filed: November 11, 2021
    Publication date: March 3, 2022
    Applicant: The University of Chicago
    Inventors: Nicolas Y. Masse, Gregory D. Grant, David J. Freedman
  • Patent number: 11205097
    Abstract: A computing device may receive a first set of training data for training an ANN to predict output data for a first task, and may train the ANN with the first set of training data by only adjusting values of weights associated with a first subset of neurons, the first subset selected based on an identity of the first task. The computing device may receive a second, different set of training data for training the ANN to predict output data for a second task, and may train the ANN with the second set of training data by only adjusting values of weights associated with a second subset of neurons, the second subset selected based on an identity of the second task. During training, adjusting of the value of any weight may entail weight stabilization that depends on whether there has been any training for one or more previous tasks.
    Type: Grant
    Filed: January 28, 2020
    Date of Patent: December 21, 2021
    Assignee: THE UNIVERSITY OF CHICAGO
    Inventors: Nicolas Y. Masse, Gregory D. Grant, David J. Freedman
  • Publication number: 20200250483
    Abstract: A computing device may receive a first set of training data for training an ANN to predict output data for a first task, and may train the ANN with the first set of training data by only adjusting values of weights associated with a first subset of neurons, the first subset selected based on an identity of the first task. The computing device may receive a second, different set of training data for training the ANN to predict output data for a second task, and may train the ANN with the second set of training data by only adjusting values of weights associated with a second subset of neurons, the second subset selected based on an identity of the second task. During training, adjusting of the value of any weight may entail weight stabilization that depends on whether there has been any training for one or more previous tasks.
    Type: Application
    Filed: January 28, 2020
    Publication date: August 6, 2020
    Applicant: The University of Chicago
    Inventors: Nicolas Y. Masse, Gregory D. Grant, David J. Freedman