Practical Boolean Backpropagation

Simon Golbert
5/1/2025
cs.LGcs.AI

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Boolean Logic as an Error feedback mechanism

85% match2024

Towards Narrowing the Generalization Gap in Deep Boolean Networks

82% match2024

Learning with Boolean threshold functions

82% match2026

Boolean Variation and Boolean Logic BackPropagation

82% match2023

MinBackProp -- Backpropagating through Minimal Solvers

80% match1 repo92024

BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training

80% match2025

Cite this paper

@article{golbert2025practical,
  title  = {Practical Boolean Backpropagation},
  author = {Simon Golbert},
  year   = {2025},
  eprint = {2505.03791},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.03791v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.03791.svg)](https://codeofpaper.com/paper/2505.03791)

Discussion