# Efficient Stochastic Inference of Bitwise Deep Neural Networks

arXiv: https://arxiv.org/abs/1611.06539 · HTML: https://mlsanity.com/paper/1611.06539/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2016.

## Built on by (most cited first, 1 of 1)

- [Characterization and Mitigation of Insufficiencies in Automated Driving Systems](https://mlsanity.com/paper/2404.09557/) (2024)

## Abstract (arXiv)

Recently published methods enable training of bitwise neural networks which allow reduced representation of down to a single bit per weight. We present a method that exploits ensemble decisions based on multiple stochastically sampled network models to increase performance figures of bitwise neural networks in terms of classification accuracy at inference. Our experiments with the CIFAR-10 and GTSRB datasets show that the performance of such network ensembles surpasses the performance of the high-precision base model. With this technique we achieve 5.81% best classification error on CIFAR-10 test set using bitwise networks. Concerning inference on embedded systems we evaluate these bitwise networks using a hardware efficient stochastic rounding procedure. Our work contributes to efficient embedded bitwise neural networks.