Patents by Inventor Ray Jiang

Ray Jiang 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).

  • LEARNING FROM DELAYED OUTCOMES USING NEURAL NETWORKS
    Publication number: 20230244912
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning from delayed outcomes using neural networks. One of the methods includes receiving an input observation; generating, from the input observation, an output label distribution over possible labels for the input observation at a final time, comprising: processing the input observation using a first neural network configured to process the input observation to generate a distribution over possible values for an intermediate indicator at a first time earlier than the final time; generating, from the distribution, an input value for the intermediate indicator; and processing the input value for the intermediate indicator using a second neural network configured to process the input value for the intermediate indicator to determine the output label distribution over possible values for the input observation at the final time; and providing an output derived from the output label distribution.
    Type: Application
    Filed: April 6, 2023
    Publication date: August 3, 2023
    Inventors: Huiyi Hu, Ray Jiang, Timothy Arthur Mann, Sven Adrian Gowal, Balaji Lakshminarayanan, András György
  • Learning from delayed outcomes using neural networks
    Patent number: 11714994
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning from delayed outcomes using neural networks. One of the methods includes receiving an input observation; generating, from the input observation, an output label distribution over possible labels for the input observation at a final time, comprising: processing the input observation using a first neural network configured to process the input observation to generate a distribution over possible values for an intermediate indicator at a first time earlier than the final time; generating, from the distribution, an input value for the intermediate indicator; and processing the input value for the intermediate indicator using a second neural network configured to process the input value for the intermediate indicator to determine the output label distribution over possible values for the input observation at the final time; and providing an output derived from the output label distribution.
    Type: Grant
    Filed: March 11, 2019
    Date of Patent: August 1, 2023
    Assignee: DeepMind Technologies Limited
    Inventors: Huiyi Hu, Ray Jiang, Timothy Arthur Mann, Sven Adrian Gowal, Balaji Lakshminarayanan, András György
  • LEARNING FROM DELAYED OUTCOMES USING NEURAL NETWORKS
    Publication number: 20190279076
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning from delayed outcomes using neural networks. One of the methods includes receiving an input observation; generating, from the input observation, an output label distribution over possible labels for the input observation at a final time, comprising: processing the input observation using a first neural network configured to process the input observation to generate a distribution over possible values for an intermediate indicator at a first time earlier than the final time; generating, from the distribution, an input value for the intermediate indicator; and processing the input value for the intermediate indicator using a second neural network configured to process the input value for the intermediate indicator to determine the output label distribution over possible values for the input observation at the final time; and providing an output derived from the output label distribution.
    Type: Application
    Filed: March 11, 2019
    Publication date: September 12, 2019
    Inventors: Huiyi Hu, Ray Jiang, Timothy Arthur Mann, Sven Adrian Gowal, Balaji Lakshminarayanan, Andras Gyorgy