Bridge deep learning to the physical world: An efficient method to quantize network

Pei Hen Hung, Chia-Han Lee, Shao Wen Yang, V. Srinivasa Somayazulu, Yen Kuang Chen, Shao Yi Chien

研究成果: Conference contribution同行評審

8 引文 斯高帕斯(Scopus)

摘要

As better performance is achieved by deep convolutional network with more and more layers, the increasing number of weighting and bias parameters makes it only possible to be implemented on servers in cyber space but infeasible to be deployed in physical-world embedded systems because of huge storage and memory bandwidth requirements. In this paper, we proposed an efficient method to quantize the model parameters. Instead of taking the quantization process as a negative effect on precision, we regarded it as a regularize problem to prevent overfitting, and a two-stage quantization technique including soft- and hard-quantization is developed. With the help of our quantization method, not only 93.75% of the parameter memory size can be reduced by replacing the word length from 32-bit to 2-bit, but the testing accuracy after quantization is also better than previous approaches in some dataset, and the additional training overhead is only 3% of the ordinary one.

原文English
主出版物標題Electronic Proceedings of the 2015 IEEE International Workshop on Signal Processing Systems, SiPS 2015
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781467396042
DOIs
出版狀態Published - 2 十二月 2015
事件IEEE International Workshop on Signal Processing Systems, SiPS 2015 - Hangzhou, China
持續時間: 14 十月 201516 十月 2015

出版系列

名字IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation
2015-December
ISSN(列印)1520-6130

Conference

ConferenceIEEE International Workshop on Signal Processing Systems, SiPS 2015
國家/地區China
城市Hangzhou
期間14/10/1516/10/15

指紋

深入研究「Bridge deep learning to the physical world: An efficient method to quantize network」主題。共同形成了獨特的指紋。

引用此