PACKING MACHINE LEARNING MODELS USING PRUNING AND PERMUTATION

An example system includes a processor to prune a machine learning model based on an importance of neurons or weights. The processor is to further permute and pack remaining neurons or weights of the pruned machine learning model to reduce an amount of ciphertext computation under a selected constra...

Full description

Saved in:
Bibliographic Details
Main Authors PAL, Subhankar, BUYUKTOSUNOGLU, Alper, VACULIN, Roman, AHARONI, Ehud, SOCEANU, Omri, SARPATWAR, Kanthi, DRUCKER, Nir, SHAUL, Hayim, BARUCH, Moran, BOSE, Pradip
Format Patent
LanguageEnglish
French
Published 11.01.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:An example system includes a processor to prune a machine learning model based on an importance of neurons or weights. The processor is to further permute and pack remaining neurons or weights of the pruned machine learning model to reduce an amount of ciphertext computation under a selected constraint. Un système donné à titre d'exemple comprend un processeur conçu pour élaguer un modèle d'apprentissage automatique sur la base d'une importance de neurones ou de poids. Le processeur est conçu en outre pour permuter et conditionner des neurones ou des poids restants du modèle d'apprentissage automatique élagué, afin de réduire une quantité de calcul de texte chiffré selon une contrainte sélectionnée.
Bibliography:Application Number: WO2023IB55565