Patents by Inventor Maxim Milakov

Maxim Milakov 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).

  • TECHNIQUES FOR OPTIMIZING NEURAL NETWORKS
    Publication number: 20220188608
    Abstract: Apparatuses, systems, and techniques to cache and reuse data for a neural network. In at least one embodiment, data generated by one or more layers of a neural network is cached and reused by the neural network.
    Type: Application
    Filed: December 15, 2020
    Publication date: June 16, 2022
    Inventors: Gregory Heinrich, Maxim Milakov, Xin Tong, Yue Wu
  • AUTOMATED METHODS FOR CONVERSIONS TO A LOWER PRECISION DATA FORMAT
    Publication number: 20210256348
    Abstract: Aspects of the present invention are directed to computer-implemented techniques for performing data compression and conversion between data formats of varying degrees of precision, and more particularly for improving the inferencing (application) of artificial neural networks using a reduced precision (e.g., INT8) data format. Embodiments of the present invention generate candidate conversions of data output, then employ a relative measure of quality to identify the candidate conversion with the greatest accuracy (i.e., least divergence from the original higher precision values). The representation can be then be used during inference to perform computations on the resulting output data.
    Type: Application
    Filed: May 3, 2021
    Publication date: August 19, 2021
    Inventors: Szymon Migacz, Hao Wu, Dilip Sequeira, Ujval Kapasi, Maxim Milakov, Slawomir Kierat, Zacky Zhou, Yilin Zhang, Alex Fit-Florea
  • Automated methods for conversions to a lower precision data format
    Patent number: 10997492
    Abstract: Aspects of the present invention are directed to computer-implemented techniques for performing data compression and conversion between data formats of varying degrees of precision, and more particularly for improving the inferencing (application) of artificial neural networks using a reduced precision (e.g., INT8) data format. Embodiments of the present invention generate candidate conversions of data output, then employ a relative measure of quality to identify the candidate conversion with the greatest accuracy (i.e., least divergence from the original higher precision values). The representation can be then be used during inference to perform computations on the resulting output data.
    Type: Grant
    Filed: December 11, 2017
    Date of Patent: May 4, 2021
    Assignee: Nvidia Corporation
    Inventors: Szymon Migacz, Hao Wu, Dilip Sequeira, Ujval Kapasi, Maxim Milakov, Slawomir Kierat, Zacky Zhou, Yilin Zhang, Alex Fit-Florea
  • AUTOMATED METHODS FOR CONVERSIONS TO A LOWER PRECISION DATA FORMAT
    Publication number: 20180211152
    Abstract: Aspects of the present invention are directed to computer-implemented techniques for performing data compression and conversion between data formats of varying degrees of precision, and more particularly for improving the inferencing (application) of artificial neural networks using a reduced precision (e.g., INT8) data format. Embodiments of the present invention generate candidate conversions of data output, then employ a relative measure of quality to identify the candidate conversion with the greatest accuracy (i.e., least divergence from the original higher precision values). The representation can be then be used during inference to perform computations on the resulting output data.
    Type: Application
    Filed: December 11, 2017
    Publication date: July 26, 2018
    Inventors: Szymon Migacz, Hao Wu, Dilip Sequeira, Ujval Kapasi, Maxim Milakov, Slawomir Kierat, Zacky Zhou, Yilin Zhang, Alex Fit-Florea