pith. sign in

arxiv: 1809.03368 · v1 · pith:OVH2LWT2new · submitted 2018-09-10 · 💻 cs.LG · stat.ML

Probabilistic Binary Neural Networks

classification 💻 cs.LG stat.ML
keywords neuralbinaryblrnetnetworkactivationsneednetworksprobabilistic
0
0 comments X
read the original abstract

Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both binary weights and activations, called BLRNet. By embracing stochasticity during training, we circumvent the need to approximate the gradient of non-differentiable functions such as sign(), while still obtaining a fully Binary Neural Network at test time. Moreover, it allows for anytime ensemble predictions for improved performance and uncertainty estimates by sampling from the weight distribution. Since all operations in a layer of the BLRNet operate on random variables, we introduce stochastic versions of Batch Normalization and max pooling, which transfer well to a deterministic network at test time. We evaluate the BLRNet on multiple standardized benchmarks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.