Patents by Inventor Petr Zadrazil

Petr Zadrazil 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).

  • Compression of Data that Exhibits Mixed Compressibility
    Publication number: 20240080038
    Abstract: Systems and methods for compression of data that exhibits mixed compressibility, such as floating-point data, are provided. As one example, aspects of the present disclosure can be used to compress floating-point data that represents the values of parameters of a machine-learned model. Therefore, aspects of the present disclosure can be used to compress machine-learned models (e.g., for reducing storage requirements associated with the model, reducing the bandwidth expended to transmit the model, etc.).
    Type: Application
    Filed: October 27, 2023
    Publication date: March 7, 2024
    Inventors: Giovanni Motta, Francoise Beaufays, Petr Zadrazil
  • Compression of data that exhibits mixed compressibility
    Patent number: 11843397
    Abstract: Systems and methods for compression of data that exhibits mixed compressibility, such as floating-point data, are provided. As one example, aspects of the present disclosure can be used to compress floating-point data that represents the values of parameters of a machine-learned model. Therefore, aspects of the present disclosure can be used to compress machine-learned models (e.g., for reducing storage requirements associated with the model, reducing the bandwidth expended to transmit the model, etc.).
    Type: Grant
    Filed: September 9, 2019
    Date of Patent: December 12, 2023
    Assignee: GOOGLE LLC
    Inventors: Giovanni Motta, Francoise Beaufays, Petr Zadrazil
  • Compression of Data that Exhibits Mixed Compressibility
    Publication number: 20220368343
    Abstract: Systems and methods for compression of data that exhibits mixed compressibility, such as floating-point data, are provided. As one example, aspects of the present disclosure can be used to compress floating-point data that represents the values of parameters of a machine-learned model. Therefore, aspects of the present disclosure can be used to compress machine-learned models (e.g., for reducing storage requirements associated with the model, reducing the bandwidth expended to transmit the model, etc.).
    Type: Application
    Filed: September 9, 2019
    Publication date: November 17, 2022
    Inventors: Giovanni Motta, Francoise Beaufays, Petr Zadrazil