Patents Assigned to Fabula AI Limited
  • System and a method for learning features on geometric domains
    Patent number: 10210430
    Abstract: A method for extracting hierarchical features from data defined on a geometric domain is provided. The method includes applying on said data at least an intrinsic convolution layer, including the steps of applying a patch operator to extract a local representation of the input data around a point on the geometric domain and outputting the correlation of a patch resulting from the extraction with a plurality of templates. A system to implement the method is also described.
    Type: Grant
    Filed: November 22, 2017
    Date of Patent: February 19, 2019
    Assignee: Fabula AI Limited
    Inventors: Michael Bronstein, Davide Boscaini, Federico Monti