Patents by Inventor Anton Alexandrov

Anton Alexandrov 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).

  • Pairwise ranking using neural networks
    Patent number: 11989649
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to generate a ranking score for a network input. One of the methods includes generating training data and training the neural network on the training data. The training data includes a plurality of training pairs. The generating comprising: obtaining data indicating that a plurality of training network inputs were displayed in a user interface according to a presentation order, obtaining data indicating that a first training network input of the plurality of training network inputs has a positive label, determining that a second training network input of the plurality of training network inputs (i) has a negative label and (ii) is higher than the first training network input in the presentation order, and generating a training pair that includes the first training network input and the second training network input.
    Type: Grant
    Filed: November 18, 2020
    Date of Patent: May 21, 2024
    Assignee: DeepMind Technologies Limited
    Inventors: Xiaohong Gong, Arturo Bajuelos Castillo, Sanjeev Jagannatha Rao, Xueliang Lu, Amogh S. Asgekar, Anton Alexandrov, Carsten Miklos Steinebach
  • PAIRWISE RANKING USING NEURAL NETWORKS
    Publication number: 20210406680
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to generate a ranking score for a network input. One of the methods includes generating training data and training the neural network on the training data. The training data includes a plurality of training pairs. The generating comprising: obtaining data indicating that a plurality of training network inputs were displayed in a user interface according to a presentation order, obtaining data indicating that a first training network input of the plurality of training network inputs has a positive label, determining that a second training network input of the plurality of training network inputs (i) has a negative label and (ii) is higher than the first training network input in the presentation order, and generating a training pair that includes the first training network input and the second training network input.
    Type: Application
    Filed: November 18, 2020
    Publication date: December 30, 2021
    Inventors: Xiaohong Gong, Arturo Bajuelos Castillo, Sanjeev Jagannatha Rao, Xueliang Lu, Amogh S. Asgekar, Anton Alexandrov, Carsten Miklos Steinebach