Komprimierung von Tiefenlernmodellen

Details

Veröffentlichungs-Nr.

EP4790596

Anmeldetag

10. Februar 2025

Veröffentlichung

12. August 2026

Rechtsraum

EP

Abstract

A computer-implemented method comprising: determining, in an Al system comprising a deep learning model with a plurality of layers defining a weight matrix of the model, groups of two or more contiguous layers in the plurality of layers; for each determined group of two or more contiguous layers, applying SVD to weights of one layer of the group; for each layer with SVD applied thereto, truncating at least some singular values obtained from the application of the SVD based on at least one truncation criterion; for each determined group of two or more contiguous layers, selecting a plurality of output channels of the deep learning model for removal based on at least one weight importance criterion; and for each determined group of two or more contiguous layers, removing one or more input channels and/or one or more output channels based on the selected plurality of output channels such that a shared dimension size in the group is maintained. Also, an apparatus and a computer program.

Anmelder

Firma

Multiverse Computing S.L.

Land

🇪🇸 Spanien