The paper introduces and compares gradient estimators for stochastic binary neurons, notably a decomposition approach and the straight-through estimator, to support sparse conditional computation in deep networks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2013 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
The paper introduces and compares gradient estimators for stochastic binary neurons, notably a decomposition approach and the straight-through estimator, to support sparse conditional computation in deep networks.