Showing stat.MLShow all
2 papers · 1 filter
stat.ML2020
Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks
Alexander Shekhovtsov, Viktor Yanush, Boris Flach
In neural networks with binary activations and or binary weights the training by gradient descent is complicated as the model has piecewise constant response. We consider stochasti…
stat.ML2018
Feed-forward Uncertainty Propagation in Belief and Neural Networks
Alexander Shekhovtsov, Boris Flach, Michal Busta
We propose a feed-forward inference method applicable to belief and neural networks. In a belief network, the method estimates an approximate factorized posterior of all hidden uni…