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