English

$\partial\mathbb{B}$ nets: learning discrete functions by gradient descent

Machine Learning 2023-05-15 v1 Neural and Evolutionary Computing

Abstract

B\partial\mathbb{B} nets are differentiable neural networks that learn discrete boolean-valued functions by gradient descent. B\partial\mathbb{B} nets have two semantically equivalent aspects: a differentiable soft-net, with real weights, and a non-differentiable hard-net, with boolean weights. We train the soft-net by backpropagation and then `harden' the learned weights to yield boolean weights that bind with the hard-net. The result is a learned discrete function. `Hardening' involves no loss of accuracy, unlike existing approaches to neural network binarization. Preliminary experiments demonstrate that B\partial\mathbb{B} nets achieve comparable performance on standard machine learning problems yet are compact (due to 1-bit weights) and interpretable (due to the logical nature of the learnt functions).

Keywords

Cite

@article{arxiv.2305.07315,
  title  = {$\partial\mathbb{B}$ nets: learning discrete functions by gradient descent},
  author = {Ian Wright},
  journal= {arXiv preprint arXiv:2305.07315},
  year   = {2023}
}

Comments

17 pages, 8 figures

R2 v1 2026-06-28T10:32:44.258Z