Patents by Inventor Heishiro KANAGAWA

Heishiro KANAGAWA 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).

  • Cross-domain recommender systems using domain separation networks and autoencoders
    Patent number: 11699095
    Abstract: A training apparatus includes an acquiring unit that acquires a first model including an input layer to which input information is input; a plurality of intermediate layers that executes a calculation based on a feature of the input information that has been input; and an output layer that outputs output information that corresponds to output of the intermediate layer. The training apparatus includes a training unit that trains the first model such that, when predetermined input information is input to the first model, the first model outputs predetermined output information that corresponds to the predetermined input information and intermediate information output from a predetermined intermediate layer among the intermediate layers becomes close to feature information that corresponds to a feature of correspondence information that corresponds to the predetermined input information.
    Type: Grant
    Filed: January 17, 2019
    Date of Patent: July 11, 2023
    Assignee: YAHOO JAPAN CORPORATION
    Inventors: Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami
  • TRAINING APPARATUS, TRAINING METHOD, AND NON-TRANSITORY COMPUTER READABLE STORAGE MEDIUM
    Publication number: 20190228336
    Abstract: According to one aspect of an training apparatus includes an acquiring unit that acquires a first model including an input layer to which input information is input; a plurality of intermediate layers that executes a calculation based on a feature of the input information that has been input; and an output layer that outputs output information that corresponds to output of the intermediate layer. The training apparatus includes a training unit that trains the first model such that, when predetermined input information is input to the first model, the first model outputs predetermined output information that corresponds to the predetermined input information and intermediate information output from a predetermined intermediate layer among the intermediate layers becomes close to feature information that corresponds to a feature of correspondence information that corresponds to the predetermined input information.
    Type: Application
    Filed: January 17, 2019
    Publication date: July 25, 2019
    Applicant: YAHOO JAPAN CORPORATION
    Inventors: Heishiro KANAGAWA, Hayato KOBAYASHI, Nobuyuki SHIMIZU, Yukihiro TAGAMI