mlsanityData to 14 Oct 2026

Practical Boolean Backpropagation

arXiv 2505.03791 ↗First posted 1 May 2025cs.LG cs.AIcited by 0

Not on the map. Why?

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.

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

2 of 2 references.

References · 2

  1. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  2. 2024The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bitscited by 308

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning with Boolean threshold functions
  2. 2026Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networks
  3. 2024Towards Narrowing the Generalization Gap in Deep Boolean Networks
  4. 2026Fitting Multilinear Polynomials for Logic Gate Networks
  5. 2026Differentiable Logic Synthesis: Spectral Coefficient Selection via Sinkhorn-Constrained Composition
  6. 2023partialmathbbB nets: learning discrete functions by gradient descent
  7. 2021Reverse Derivative Ascent: A Categorical Approach to Learning Boolean Circuits
  8. 2025Minimalist Softmax Attention Provably Learns Constrained Boolean Functions