Papers โ€บ โˆ‚๐”น nets: learning discrete functions by gradient descent

โˆ‚๐”น nets: learning discrete functions by gradient descent

12 May 2023arXiv:2305.07315archive 2025-07-28

Ian Wright

โˆ‚๐”น nets are differentiable neural networks that learn discrete boolean-valued functions by gradient descent. โˆ‚๐”น 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 โˆ‚๐”น 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).

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

z80coder/db-nets officialmentioned in papermentioned on GitHubjaxSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Binarization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change ยท a person checks every report against the paper or source before anything changes; decisions are listed on /corrections