Patent · US Active

Deep convolutional neural network acceleration and compression method based on parameter quantification

US10970617B2 · kind B2 · utility

3Cited by

0References

2Claims

0Family size

Assignee

Institute of Automation, Chinese Academy of Sciences · CN

Inventors

Jian Cheng · Jingwei, CN
Jiaxiang Wu · Lo Wu, CN
Cong Leng · Beijing, CN
Hanqing Lu · Beijing, CN

Key dates

Filing date	Aug 21, 2015
Grant date	Apr 6, 2021
Priority date	—
Expiry date	Apr 25, 2037

Classification

Technology area (CPC G)Physics
CPC primaryG06V10/454
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

An acceleration and compression method for a deep convolutional neural network based on quantization of a parameter provided by the present application comprises: quantizing the parameter of the deep convolutional neural network to obtain a plurality of subcode books and respective corresponding index values of the plurality of subcode books; acquiring an output feature map of the deep convolutional neural network according to the plurality of subcode books and respective corresponding index values of the plurality of subcode books. The present application may implement the acceleration and compression for a deep convolutional neural network.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.