Patents by Inventor Devora BERLOWITZ

Devora BERLOWITZ 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: 20250077871
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for privacy-sensitive training of a neural network. In one aspect, a system comprises a central memory configured to store current values of a set of neural network parameters and one or more computers that are configured to implement a plurality of worker computing units, where each worker computing unit is configured to repeatedly perform operations comprising obtaining current values of the set of neural network parameters from the central memory, sampling a batch of network inputs from a set of training data, determining a respective gradient corresponding to each network input, determining an aggregated gradient based on the gradients, identifying a subset of a set of gradient values as target values, generating a noisy gradient by combining random noise with the target gradient values, and updating the current values of the set of neural network parameters.
    Type: Application
    Filed: May 25, 2023
    Publication date: March 6, 2025
    Inventors: Devora Berlowitz, Steve Shaw-Tang Chien, Yunqi Xue, Lin Ning, Shuang Song, Mei Chen
  • Patent number: 11646063
    Abstract: It is an object of the disclosed technique to provide a novel method and system for shared concurrent access to a memory cell. In accordance with the disclosed technique, there is thus provided a system for shared concurrent access to a memory cell, which includes at least one shared memory cell, an evaluator and a plurality of processing agents coupled to the input of the evaluator. The evaluator is further coupled with the at least one memory cell. The evaluator is configured to evaluate an expression for performing multiple concurrent composite assignments on the at least one shared memory cell. The evaluator further allows each of the plurality of processing agents to perform concurrent composite assignments on the at least one shared memory cell. The composite assignments do not include a read operation of the at least one shared memory cell by the plurality of processing agents.
    Type: Grant
    Filed: July 24, 2019
    Date of Patent: May 9, 2023
    Assignee: JERUSALEM COLLEGE OF TECHNOLOGY
    Inventors: Shimon Mizrahi, Raphael Berakhael Yehezkael, Ruben Attia, Erez Lax, Devora Berlowitz, Moshe Goldstein, David Dayan
  • Publication number: 20210225416
    Abstract: It is an object of the disclosed technique to provide a novel method and system for shared concurrent access to a memory cell. In accordance with the disclosed technique, there is thus provided a system for shared concurrent access to a memory cell, which includes at least one shared memory cell, an evaluator and a plurality of processing agents coupled to the input of the evaluator. The evaluator is further coupled with the at least one memory cell. The evaluator is configured to evaluate an expression for performing multiple concurrent composite assignments on the at least one shared memory cell. The evaluator further allows each of the plurality of processing agents to perform concurrent composite assignments on the at least one shared memory cell. The composite assignments do not include a read operation of the at least one shared memory cell by the plurality of processing agents.
    Type: Application
    Filed: July 24, 2019
    Publication date: July 22, 2021
    Applicant: JERUSALEM COLLEGE OF TECHNOLOGY
    Inventors: Shimon MIZRAHI, Raphael Berakhael YEHEZKAEL, Ruben ATTIA, Erez LAX, Devora BERLOWITZ, Moshe GOLDSTEIN, David DAYAN