HackerPapers

arXiv:2411.04732cs.LG

Convolutional Differentiable Logic Gate Networks

Felix Petersen, Hilde Kuehne, Christian Borgelt, Julian Welzel, Stefano Ermon

Abstract

With the increasing inference cost of machine learning models, there is a growing interest in models with fast and efficient inference. Recently, an approach for learning logic gate networks directly via a differentiable relaxation was proposed. Logic gate networks are faster than conventional neural network approaches because their inference only requires logic gate operators such as NAND, OR, and XOR, which are the underlying building blocks of current hardware and can be efficiently executed. We build on this idea, extending it by deep logic gate tree convolutions, logical OR pooling, and residual initializations. This allows scaling logic gate networks up by over one order of magnitude and utilizing the paradigm of convolution. On CIFAR-10, we achieve an accuracy of 86.29% using only 61 million logic gates, which improves over the SOTA while being 29x smaller.

arXiv comments
Published at NeurIPS 2024 (Oral)
Journal reference
DOI
Subjects
cs.LGMachine Learning cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 4 identifiable commenters in 4 comments across 4 threads, from Nov 2024 to May 2025. Found in 2 HN submissions from Nov 2024 to Nov 2024. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments4 threads

  1. Compiling a neural net to C for a speedup 1 comment

    • > What's the innovation here? > Having a distribution to pick from? As I understand it, it's exactly this. Specifically, representing neurons in a neural network via a probability distribution of logic gates and then collapsing the distribution into the optimal logic gate for a…

      awesomeMilouView on HNParent context

  2. STEPS Toward the Reinvention of Programming (2012) [pdf] 1 comment
  3. Convolutional Differentiable Logic Gate Networks 1 comment

    • "Convolutional Differentiable Logic Gate Networks" (2024) https://arxiv.org/abs/2411.04732 : > With the increasing inference cost of machine learning models, there is a growing interest in models with fast and efficient inference. Recently, an approach for learning logic gate…

      westurnerView on HNParent context

  4. Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference 1 comment

    • See Convolutional Differentiable Logic Gate Networks https://arxiv.org/abs/2411.04732 , which is a small step in that direction.

      jacobgormView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.