Method and computer tool for determining functions for transfer between pairs of successive layers of a neural network

Abstract

An embodiment of the disclosure relates to a method and computer tool for determining functions for transfer between pairs of successive layers of a neural network. The method can be performed prior to implementation of a neural network by a processing unit. The neural network comprising a succession of layers and at least one operator applied between at least one pair of successive layers. A computational tool generates an executable code intended to be executed by the processing unit in order to implement the neural network. The computational tool generates at least one transfer function between the at least one pair of layers taking the form of a set of pre-computed values.

Description

[0001] Cross References to Related Applications [0002] This application claims priority from European Patent Application No. 19290051.2 filed on 10 July 2019, which is hereby incorporated by reference. technical field [0003] Implementation modes and embodiments of the present invention relate to a method for implementing a neural network. Background technique [0004] Neural networks are widely used to solve various statistical problems, especially data classification problems. [0005] After a machine learning phase that is usually supervised (i.e. implemented using a classified reference database), the neural network autonomously "learns" and becomes able to apply the same classification to unseen data. [0006] Mention may be made of a convolutional neural network (CNN), a type of neural network in which the connection pattern between two layers is inspired by the visual cortex of animals. Such neural networks allow efficient recognition of objects or people in ima...

AI Technical Summary

Problems solved by technology

[0024] This is done in real-time by the processor executing the neural network and is completely inefficient in terms of computation time and memory

Images