A variational Bayesian framework with importance-weighted straight-through estimators trains binary and spiking networks without normalization layers, matching surrogate-gradient baselines on CIFAR-10, DVS Gesture, and SHD.
Understanding straight-through estimator in train- ing activation quantized neural nets
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
support 1representative citing papers
citing papers explorer
-
A Principled Bayesian Framework for Training Binary and Spiking Neural Networks
A variational Bayesian framework with importance-weighted straight-through estimators trains binary and spiking networks without normalization layers, matching surrogate-gradient baselines on CIFAR-10, DVS Gesture, and SHD.