Patents by Inventor Karel Lenc

Karel Lenc 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).

  • NOWCASTING USING GENERATIVE NEURAL NETWORKS
    Publication number: 20240176045
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for precipitation nowcasting using generative neural networks.
    Type: Application
    Filed: February 16, 2022
    Publication date: May 30, 2024
    Inventors: Suman Ravuri, Karel Lenc, Piotr Wojciech Mirowski, Remi Roger Alain Paul Lam, Matthew James Willson, Andrew Brock
  • LANGUAGE MODEL FOR PROCESSING A MULTI-MODE QUERY INPUT
    Publication number: 20230350936
    Abstract: A query processing system is described which receives a query input comprising an input token string and also at least one data item having a second, different modality, and generates a corresponding output token string.
    Type: Application
    Filed: April 28, 2023
    Publication date: November 2, 2023
    Inventors: Jean-Baptiste Alayrac, Jeffrey Donahue, Karel Lenc, Karen Simonyan, Malcolm Kevin Campbell Reynolds, Pauline Luc, Arthur Mensch, Iain Barr, Antoine Miech, Yana Elizabeth Hasson, Katherine Elizabeth Millican, Roman Ring
  • Learning non-differentiable weights of neural networks using evolutionary strategies
    Patent number: 11676035
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. The neural network has a plurality of differentiable weights and a plurality of non-differentiable weights. One of the methods includes determining trained values of the plurality of differentiable weights and the non-differentiable weights by repeatedly performing operations that include determining an update to the current values of the plurality of differentiable weights using a machine learning gradient-based training technique and determining, using an evolution strategies (ES) technique, an update to the current values of a plurality of distribution parameters.
    Type: Grant
    Filed: January 23, 2020
    Date of Patent: June 13, 2023
    Assignee: DeepMind Technologies Limited
    Inventors: Karel Lenc, Karen Simonyan, Tom Schaul, Erich Konrad Elsen
  • LEARNING NON-DIFFERENTIABLE WEIGHTS OF NEURAL NETWORKS USING EVOLUTIONARY STRATEGIES
    Publication number: 20200234142
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. The neural network has a plurality of differentiable weights and a plurality of non-differentiable weights. One of the methods includes determining trained values of the plurality of differentiable weights and the non-differentiable weights by repeatedly performing operations that include determining an update to the current values of the plurality of differentiable weights using a machine learning gradient-based training technique and determining, using an evolution strategies (ES) technique, an update to the current values of a plurality of distribution parameters.
    Type: Application
    Filed: January 23, 2020
    Publication date: July 23, 2020
    Inventors: Karel Lenc, Karen Simonyan, Tom Schaul, Erich Konrad Elsen