Invention Grant
- Patent Title: System and a method for learning features on geometric domains
-
Application No.: US15820909Application Date: 2017-11-22
-
Publication No.: US10210430B2Publication Date: 2019-02-19
- Inventor: Michael Bronstein , Davide Boscaini , Federico Monti
- Applicant: Fabula AI Limited
- Applicant Address: GB London
- Assignee: Fabula AI Limited
- Current Assignee: Fabula AI Limited
- Current Assignee Address: GB London
- Agency: Saliwanchik, Lloyd & Eisenschenk
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06K9/48 ; G06K9/52 ; G06F17/14 ; G06K9/00 ; G06N3/04 ; G06T19/00

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.
Public/Granted literature
- US20180096229A1 SYSTEM AND A METHOD FOR LEARNING FEATURES ON GEOMETRIC DOMAINS Public/Granted day:2018-04-05
Information query