English

Practical Boolean Backpropagation

Machine Learning 2025-05-08 v1 Artificial Intelligence

Abstract

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.

Cite

@article{arxiv.2505.03791,
  title  = {Practical Boolean Backpropagation},
  author = {Simon Golbert},
  journal= {arXiv preprint arXiv:2505.03791},
  year   = {2025}
}

Comments

11 pages