Patents by Inventor Nicholas Myles Wisener Frosst

Nicholas Myles Wisener Frosst 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).

  • Neural network training using the soft nearest neighbor loss
    Patent number: 11941867
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a classification neural network.
    Type: Grant
    Filed: January 22, 2020
    Date of Patent: March 26, 2024
    Assignee: Google LLC
    Inventors: Geoffrey E. Hinton, Nicholas Myles Wisener Frosst, Nicolas Guy Robert Papernot
  • Capsule neural networks
    Patent number: 11694060
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network that is configured to receive a network input and to generate a network output for the network input. The neural network comprises a plurality of layers arranged in a sequence, including a plurality of capsule layers. Each particular capsule in a particular capsule layer is configured to receive respective inputs including: (i) outputs generated by capsules of a previous capsule layer that is before the particular capsule layer in the sequence, and (ii) final routing factors between capsules of the previous capsule layer and the particular capsule, wherein the final routing factors are generated by a routing subsystem. Each particular capsule in the particular capsule layer is configured to determine a particular capsule output based on the received inputs, wherein the particular capsule output is of dimension greater than one.
    Type: Grant
    Filed: October 4, 2022
    Date of Patent: July 4, 2023
    Assignee: Google LLC
    Inventors: Geoffrey E. Hinton, Nicholas Myles Wisener Frosst, Sara Sabour Rouh Aghdam
  • System and Method for Training Language Models Using Already Trained Language Models
    Publication number: 20230177279
    Abstract: The present disclosure relates to a system, method and non-transitory computer readable medium for training language models. The exemplary method includes obtaining a first language model. The method includes using a determined set of weights of the first language model to initialize a second language model. The first and second language model are different model types. The method includes applying the second language model to perform an operation.
    Type: Application
    Filed: November 30, 2022
    Publication date: June 8, 2023
    Applicant: Cohere Inc.
    Inventors: Nicholas Myles Wisener FROSST, Rozhina GHANAVI, Christopher Alexander CREMER
  • CAPSULE NEURAL NETWORKS
    Publication number: 20230027069
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network that is configured to receive a network input and to generate a network output for the network input. The neural network comprises a plurality of layers arranged in a sequence, including a plurality of capsule layers. Each particular capsule in a particular capsule layer is configured to receive respective inputs including: (i) outputs generated by capsules of a previous capsule layer that is before the particular capsule layer in the sequence, and (ii) final routing factors between capsules of the previous capsule layer and the particular capsule, wherein the final routing factors are generated by a routing subsystem. Each particular capsule in the particular capsule layer is configured to determine a particular capsule output based on the received inputs, wherein the particular capsule output is of dimension greater than one.
    Type: Application
    Filed: October 4, 2022
    Publication date: January 26, 2023
    Inventors: Geoffrey E. Hinton, Nicholas Myles Wisener Frosst, Sara Sabour Rouh Aghdam
  • Capsule neural networks
    Patent number: 11494609
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network that is configured to receive a network input and to generate a network output for the network input. The neural network comprises a plurality of layers arranged in a sequence, including a plurality of capsule layers. Each particular capsule in a particular capsule layer is configured to receive respective inputs including: (i) outputs generated by capsules of a previous capsule layer that is before the particular capsule layer in the sequence, and (ii) final routing factors between capsules of the previous capsule layer and the particular capsule, wherein the final routing factors are generated by a routing subsystem. Each particular capsule in the particular capsule layer is configured to determine a particular capsule output based on the received inputs, wherein the particular capsule output is of dimension greater than one.
    Type: Grant
    Filed: December 15, 2017
    Date of Patent: November 8, 2022
    Assignee: Google LLC
    Inventors: Geoffrey E. Hinton, Nicholas Myles Wisener Frosst, Sara Sabour Rouh Aghdam
  • NEURAL NETWORK TRAINING USING THE SOFT NEAREST NEIGHBOR LOSS
    Publication number: 20220101624
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a classification neural network.
    Type: Application
    Filed: January 22, 2020
    Publication date: March 31, 2022
    Inventors: Geoffrey E. Hinton, Nicholas Myles Wisener Frosst, Nicolas Guy Robert Papernot
  • CAPSULE NEURAL NETWORKS
    Publication number: 20200285934
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network that is configured to receive a network input and to generate a network output for the network input. The neural network comprises a plurality of layers arranged in a sequence, including a plurality of capsule layers. Each particular capsule in a particular capsule layer is configured to receive respective inputs including: (i) outputs generated by capsules of a previous capsule layer that is before the particular capsule layer in the sequence, and (ii) final routing factors between capsules of the previous capsule layer and the particular capsule, wherein the final routing factors are generated by a routing subsystem. Each particular capsule in the particular capsule layer is configured to determine a particular capsule output based on the received inputs, wherein the particular capsule output is of dimension greater than one.
    Type: Application
    Filed: December 15, 2017
    Publication date: September 10, 2020
    Inventors: Geoffrey E. Hinton, Nicholas Myles Wisener Frosst, Sara Sabour Rouh Aghdam