Patent · US Active

Methods for learning the parameters of a convolutional neural network, and for classifying an input datum

US11790222B2 · kind B2 · utility

0Cited by

0References

12Claims

0Family size

Assignee

IDEMIA IDENTITY & SECURITY FRANCE · FR

Inventors

Herve Chabanne · Courbevoie, FR
Vincent DESPIEGEL · Courbevoie, FR
Anouar Mellakh · Courbevoie, FR

Key dates

Filing date	Mar 18, 2019
Grant date	Oct 17, 2023
Priority date	—
Expiry date	Jan 14, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06V40/172
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

The present invention concerns a method for learning the parameters of a convolutional neural network, CNN, for data classification, the method comprising the implementation of steps by data processing means (11a, 11 b, 11c) of at least one server (1a, 1b, 1c), of:

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.