Title:
SYSTEMS AND METHODS FOR MACHINE LEARNING MODEL COMPRESSION
Document Type and Number:
WIPO Patent Application WO/2023/241225
Kind Code:
A1
Abstract:
The present disclosure relates to systems and methods for machine learning model compression. The method may include obtaining a plurality of weights of the machine learning model. The method may also include determining a target quantization interval set of the plurality of weights. The target quantization interval set may include a plurality of target quantization intervals. The method may further include determining a plurality of target shared weights corresponding to the plurality of target quantization intervals respectively. The plurality of target shared weights may be used to compress the machine learning model.
Inventors:
YIN JUN (CN)
HAN JIANQIANG (CN)
CHEN BOYANG (CN)
WU LI (CN)
ZHOU XIANGMING (CN)
HAN JIANQIANG (CN)
CHEN BOYANG (CN)
WU LI (CN)
ZHOU XIANGMING (CN)
Application Number:
PCT/CN2023/090365
Publication Date:
December 21, 2023
Filing Date:
April 24, 2023
Export Citation:
Assignee:
ZHEJIANG DAHUA TECHNOLOGY CO (CN)
International Classes:
G06N3/08
Foreign References:
CN114757353A | 2022-07-15 | |||
CN110119745A | 2019-08-13 | |||
US20200342288A1 | 2020-10-29 | |||
US20210027195A1 | 2021-01-28 |
Attorney, Agent or Firm:
METIS IP (CHENGDU) LLC (CN)
Download PDF:
Previous Patent: METHOD FOR BIOSYNTHESIZING NOOTKATONE AND CARRIER
Next Patent: STATEMENT GENERATION METHOD AND DEVICE AND STORAGE MEDIUM
Next Patent: STATEMENT GENERATION METHOD AND DEVICE AND STORAGE MEDIUM