NEURAL NETWORK COMPRESSION

A neural network model is trained, where the training includes multiple training iterations. Weights of a particular layer of the neural network are pruned during a forward pass of a particular one of the training iterations. During the same forward pass of the particular training iteration, values...

Full description

Saved in:
Bibliographic Details
Main Authors Park, Mi Sun, Brick, Cormac M, Xu, Xiaofan
Format Patent
LanguageEnglish
Published 03.03.2022
Subjects
BASIC ELECTRONIC CIRCUITRY
CALCULATING
CODE CONVERSION IN GENERAL
CODING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DECODING
ELECTRICITY
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:A neural network model is trained, where the training includes multiple training iterations. Weights of a particular layer of the neural network are pruned during a forward pass of a particular one of the training iterations. During the same forward pass of the particular training iteration, values of weights of the particular layer are quantized to determine a quantized-sparsified subset of weights for the particular layer. A compressed version of the neural network model is generated from the training based at least in part on the quantized-sparsified subset of weights.
Bibliography:Application Number: US201917416461