Crossmark

MXQN:Mixed quantization for reducing bit-width of weights and activations in deep convolutional neural networks

Published Online: 2021-01-04

Published Print: 2021-07

Authors

Huang, Chenglong http://orcid.org/0000-0001-6241-9745
Liu, Puguang

Fang, Liang
Funding

Funding for this research was provided by:

National Key Research & Development Program of China (No. 2018YFB1003304)
License Information

Text and Data Mining valid from 2021-01-04

Version of Record valid from 2021-01-04
More Information

Article History

Accepted: 1 December 2020

First Online: 4 January 2021

Compliance with Ethical Standards

:

: The authors declare that they have no conflict of interest.

Document is current