Patents Assigned to DeepMind Technologies
  • Patent number: 10223617
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using recurrent attention. One of the methods includes determining a location in the first image; extracting a glimpse from the first image using the location; generating a glimpse representation of the extracted glimpse; processing the glimpse representation using a recurrent neural network to update a current internal state of the recurrent neural network to generate a new internal state; processing the new internal state to select a location in a next image in the image sequence after the first image; and processing the new internal state to select an action from a predetermined set of possible actions.
    Type: Grant
    Filed: June 4, 2015
    Date of Patent: March 5, 2019
    Assignee: DeepMind Technologies Limited
    Inventors: Volodymyr Mnih, Koray Kavukcuoglu
  • Patent number: 10176424
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network system. In one aspect, a neural network system includes a recurrent neural network that is configured to, for each time step of a predetermined number of time steps, receive a set of latent variables for the time step and process the latent variables to update a hidden state of the recurrent neural network; and a generative subsystem that is configured to, for each time step, generate the set of latent variables for the time step and provide the set of latent variables as input to the recurrent neural network; update a hidden canvas using the updated hidden state of the recurrent neural network; and, for a last time step, generate an output image using the updated hidden canvas for the last time step.
    Type: Grant
    Filed: February 3, 2017
    Date of Patent: January 8, 2019
    Assignee: DeepMind Technologies Limited
    Inventors: Ivo Danihelka, Danilo Jimenez Rezende, Shakir Mohamed
  • Patent number: 10032089
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using an image processing neural network system that includes a spatial transformer module. One of the methods includes receiving an input feature map derived from the one or more input images, and applying a spatial transformation to the input feature map to generate a transformed feature map, comprising: processing the input feature map to generate spatial transformation parameters for the spatial transformation, and sampling from the input feature map in accordance with the spatial transformation parameters to generate the transformed feature map.
    Type: Grant
    Filed: June 6, 2016
    Date of Patent: July 24, 2018
    Assignee: DeepMind Technologies Limited
    Inventors: Maxwell Elliot Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu
  • Publication number: 20140185959
    Abstract: A method for processing an image to generate a signature which is characteristic of a pattern within said image. The method comprising receiving an image; overlaying a window at multiple locations on said image to define a plurality of sub-images within said image, with each sub-image each having a plurality of pixels having a luminance level; determining a luminance value for each said sub-image, wherein said luminance value is derived from said luminance levels of said plurality of pixels; and combining said luminance values for each of said sub-images to form said signature. Said combining is such that said signature is independent of the location of each sub-image. A method of creating a database of images using said method of generating signatures is also described.
    Type: Application
    Filed: January 15, 2014
    Publication date: July 3, 2014
    Applicant: DeepMind Technologies Limited
    Inventors: Benjamin Kenneth Coppin, Mustafa Suleyman, Arun Nair
  • Patent number: 8644607
    Abstract: A method is described for processing an image to generate a signature which is characteristic of a pattern within the image. The method includes: receiving an image; overlaying a window at multiple locations on the image to define a plurality of sub-images within the image, with each sub-image each having a plurality of pixels having a luminance level; determining a luminance value for each sub-image where the luminance value is derived from the luminance levels of the plurality of pixels; and combining the luminance values for each of the sub-images to form the signature. The combining is such that the signature is independent of the location of each sub-image. A method of creating a database of images using the method of generating signatures is also described.
    Type: Grant
    Filed: March 13, 2013
    Date of Patent: February 4, 2014
    Assignee: DeepMind Technologies
    Inventors: Benjamin Kenneth Coppin, Mustafa Suleyman, Arun Nair
  • Publication number: 20140019431
    Abstract: A system and method for creating a search query and for searching based on said search query. The user starts from one image and systematically refines their search in a series of steps and possibly through one or more iterations of these series of steps until they find the image or images they are looking for.
    Type: Application
    Filed: March 14, 2013
    Publication date: January 16, 2014
    Applicant: DeepMind Technologies Limited
    Inventors: Mustafa Suleyman, Benjamin Kenneth Suleyman