One-time soft alignment between forward and fixed feedback weights at initialization substantially improves feedback alignment training and approaches backpropagation accuracy on small image tasks.
Energy and policy considerations for modern deep learning research
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
One-Time Soft Alignment Enables Resilient Learning without Weight Transport
One-time soft alignment between forward and fixed feedback weights at initialization substantially improves feedback alignment training and approaches backpropagation accuracy on small image tasks.