Verfahren und System zur Komprimierung eines Neuronalen Netzes

Details

Veröffentlichungs-Nr.

EP3923199

Aktenzeichen

EP20179099

Anmeldetag

9. Juni 2020

Veröffentlichung

25. Juni 2025

Erteilung

25. Juni 2025

Rechtsraum

EP

IPC

G06N3/042G06N3/0464G06N3/0495G06N3/082// G06N3/096

Abstract

A method for compressing a neural network comprising a plurality of layers, each layer comprising a weight tensor. Said method comprises a step of selecting (E10) hyperparameters to define at least one basis of tensors referred to as "basis tensors", including a rank hyperparameter R, a dimension hyperparameter N and a size hyperparameter representative of the number of basis tensors. Said method also comprises, for each weight tensor, a set of steps of: - embedding (E20) the weight tensor into an envelope tensor, - reshaping (E30) said envelope tensor by tensorization, - determining (E40) a representation of the reshaped envelope tensor in the form of a sequence of elements comprising tensors referred to as "cores", - parameterizing (E50) each core into a combination of the basis tensors.

Anmelder

Firmen

TOYOTA JIDOSHA KABUSHIKI KAISHA
ETH Zurich - The Swiss Federal Institute of Technology Zurich

Land

🇯🇵 Japan

Fachgebiete