LGMLSep 10, 2018

Probabilistic Binary Neural Networks

arXiv:1809.03368v154 citations
AI Analysis

This work addresses the need for efficient deep neural networks for deployment in resource-constrained environments, though it is incremental in improving binary network training.

The authors tackled the challenge of training binary neural networks with both binary weights and activations by introducing a probabilistic training method called BLRNet, which avoids gradient approximation issues and achieves competitive performance on standardized benchmarks.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes