# Practical Boolean Backpropagation

arXiv: https://arxiv.org/abs/2505.03791 · HTML: https://mlsanity.com/paper/2505.03791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 2 of its 2 references that are in the map.
- First posted on arXiv 1 May 2025.

## Builds on (most cited first, 2 of 2)

- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://mlsanity.com/paper/2402.17764/) (2024)

## Abstract (arXiv)

Boolean neural networks offer hardware-efficient alternatives to real-valued models. While quantization is common, purely Boolean training remains underexplored. We present a practical method for purely Boolean backpropagation for networks based on a single specific gate we chose, operating directly in Boolean algebra involving no numerics. Initial experiments confirm its feasibility.