Learning quantized neural nets by coarse gradient method for nonlinear classification
Work
Year: 2021
Type: article
Abstract: Quantized or low-bit neural networks are attractive due to their inference efficiency. However, training deep neural networks with quantized activations involves minimizing a discontinuous and piecew... more
Authors Ziang Long, Penghang Yin, Jack Xin
Institutions University of California, Irvine, University at Albany, State University of New York, Albany State University
Cites: 31
Cited by:
Related to: 10
FWCI:
Citation percentile (by year/subfield):
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
APC paid (est): $3,590
Funder National Science Foundation
Grant ID DMS-1924935