Learning without loss
Work
Year: 2021
Type: article
Abstract: We explore a new approach for training neural networks where all loss functions are replaced by hard constraints. The same approach is very successful in phase retrieval, where signals are reconstruc... more
Author Veit Elser
Institution Cornell University
Cites: 22
Cited by: 7
Related to: 10
FWCI: 0.601
Citation percentile (by year/subfield): 78.68
Subfield: Statistical and Nonlinear Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: gold
APC paid (est): $1,283