Patent · US Active

Sparse training in neural networks

US11727268B2 · kind B2 · utility

0Cited by

3References

16Claims

0Family size

Assignee

SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD. · CN

Inventors

Zai Wang · Zhuqiao, CN
Shengyuan Zhou · Zhuqiao, CN
Shuai Hu · Beijing, CN
Tianshi Chen · Beijing, CN

Key dates

Filing date	Nov 28, 2019
Grant date	Aug 15, 2023
Priority date	—
Expiry date	Mar 9, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/126
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A computing device, comprising: a computing module, comprising one or more computing units; and a control module, comprising a computing control unit, and used for controlling shutdown of the computing unit of the computing module according to a determining condition. Also provided is a computing method. The computing device and method have the advantages of low power consumption and high flexibility, and can be combined with the upgrading mode of software, thereby further increasing the computing speed, reducing the computing amount, and reducing the computing power consumption of an accelerator.

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