NEURAL NETWORK COMPRESSION METHOD AND APPARATUS

WIPO Patent Application WO/2020/133492

A1

A neural network compression method and apparatus, used to solve the problem in the prior art that it is not possible to effectively adapt to the capability of a processing device and achieve a better processing effect. The method comprises: determining a sparse unit length according to processing capability information of a processing device; when performing a current round of training on a neural network model, according to a jth set of weights referenced in a previous round of training, adjusting the jth set of weights obtained after the previous round of training, and obtaining a jth set of weights referenced in the current round of training; performing the current round of training on the neural network model according to various obtained sets of weights referenced in the current round of training. The sparse unit length is the data length of one operation when the processing device performs matrix operations, the number of weights included in the jth set of weights is the sparse unit length, j is any positive integer from 1 to m, and m is the total number of sets of weights obtained after grouping all the weights of the neural network model according to the sparse unit length.

ZHU JIAFENG (CN)
LIU GANGYI (CN)
LU HUILI (CN)
GAO WEI (CN)
JUI SHANGLING (CN)
YANG JUNYUAN (CN)
XIA JUN (CN)

PCT/CN2018/125812

July 02, 2020

December 29, 2018

Click for automatic bibliography generation  

HUAWEI TECH CO LTD (CN)

G06N3/08; G06N3/04

CN107239825A	2017-10-10
CN107688850A	2018-02-13
CN107239824A	2017-10-10
CN107229967A	2017-10-03

TDIP & PARTNERS (CN)

View/Download PDF      PDF Help

Previous Patent: CAPABILITY REPORTING METHOD AND TERMINAL DEVICE

Next Patent: CHANNEL QUALITY REPORTING METHOD AND APPARATUS