Patents by Inventor Christopher Paul Burgess

Christopher Paul Burgess 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 visual concepts using neural networks
    Patent number: 11769057
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning visual concepts using neural networks. One of the methods includes receiving a new symbol input comprising one or more symbols from a vocabulary; and generating a new output image that depicts concepts referred to by the new symbol input, comprising: processing the new symbol input using a symbol encoder neural network to generate a new symbol encoder output for the new symbol input; sampling, from the distribution parameterized by the new symbol encoder output, a respective value for each of a plurality of visual factors; and processing a new image decoder input comprising the respective values for the visual factors using an image decoder neural network to generate the new output image.
    Type: Grant
    Filed: June 6, 2022
    Date of Patent: September 26, 2023
    Assignee: DeepMind Technologies Limited
    Inventors: Alexander Lerchner, Irina Higgins, Nicolas Sonnerat, Arka Tilak Pal, Demis Hassabis, Loic Matthey-de-l'Endroit, Christopher Paul Burgess, Matthew Botvinick
  • LEARNING VISUAL CONCEPTS USING NEURAL NETWORKS
    Publication number: 20230088555
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning visual concepts using neural networks. One of the methods includes receiving a new symbol input comprising one or more symbols from a vocabulary; and generating a new output image that depicts concepts referred to by the new symbol input, comprising: processing the new symbol input using a symbol encoder neural network to generate a new symbol encoder output for the new symbol input; sampling, from the distribution parameterized by the new symbol encoder output, a respective value for each of a plurality of visual factors; and processing a new image decoder input comprising the respective values for the visual factors using an image decoder neural network to generate the new output image.
    Type: Application
    Filed: June 6, 2022
    Publication date: March 23, 2023
    Inventors: Alexander Lerchner, Irina Higgins, Nicolas Sonnerat, Arka Tilak Pal, Demis Hassabis, Loic Matthey-de-l'Endroit, Christopher Paul Burgess, Matthew Botvinick
  • Learning visual concepts using neural networks
    Patent number: 11354823
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning visual concepts using neural networks. One of the methods includes receiving a new symbol input comprising one or more symbols from a vocabulary; and generating a new output image that depicts concepts referred to by the new symbol input, comprising: processing the new symbol input using a symbol encoder neural network to generate a new symbol encoder output for the new symbol input; sampling, from the distribution parameterized by the new symbol encoder output, a respective value for each of a plurality of visual factors; and processing a new image decoder input comprising the respective values for the visual factors using an image decoder neural network to generate the new output image.
    Type: Grant
    Filed: July 11, 2018
    Date of Patent: June 7, 2022
    Assignee: DeepMind Technologies Limited
    Inventors: Alexander Lerchner, Irina Higgins, Nicolas Sonnerat, Arka Tilak Pal, Demis Hassabis, Loic Matthey-de-l'Endroit, Christopher Paul Burgess, Matthew Botvinick
  • LEARNING VISUAL CONCEPTS USING NEURAL NETWORKS
    Publication number: 20200234468
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning visual concepts using neural networks. One of the methods includes receiving a new symbol input comprising one or more symbols from a vocabulary; and generating a new output image that depicts concepts referred to by the new symbol input, comprising: processing the new symbol input using a symbol encoder neural network to generate a new symbol encoder output for the new symbol input; sampling, from the distribution parameterized by the new symbol encoder output, a respective value for each of a plurality of visual factors; and processing a new image decoder input comprising the respective values for the visual factors using an image decoder neural network to generate the new output image.
    Type: Application
    Filed: July 11, 2018
    Publication date: July 23, 2020
    Inventors: Alexander Lerchner, Irina Higgins, Nicolas Sonnerat, Arka Tilak Pal, Demis Hassabis, Loic Matthey-de-l'Endroit, Christopher Paul Burgess, Matthew Botvinick