Convolutional Differentiable Logic Gate Networks · HackerPapers discussions

Convolutional Differentiable Logic Gate Networks — mentioned by awesomeMilou

Wed, 28 May 2025 22:35:52 GMT

> 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 given neuron via hyper-parameter tuning in the form of gradient descent. The author has a few more details in their thesis: https://arxiv.org/abs/2209.00616 Specifically it's the training approach that's patented. I'm glad to see that people are trying to improve on his method, so the patent will likely become…

Paper and discussion history. A mention is not an endorsement.

Convolutional Differentiable Logic Gate Networks — mentioned by mlajtos

Tue, 11 Mar 2025 13:21:07 GMT

No, GPUs are not needed for efficient inference. https://arxiv.org/pdf/2411.04732

Paper and discussion history. A mention is not an endorsement.

Convolutional Differentiable Logic Gate Networks — mentioned by westurner

Wed, 20 Nov 2024 02:03:40 GMT

"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 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…

Paper and discussion history. A mention is not an endorsement.

Convolutional Differentiable Logic Gate Networks — mentioned by jacobgorm

Tue, 19 Nov 2024 10:36:16 GMT

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

Paper and discussion history. A mention is not an endorsement.

Convolutional Differentiable Logic Gate Networks — HN submission

Sat, 16 Nov 2024 19:10:54 GMT

Convolutional Differentiable Logic Gate Networks

26 points; 4 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Convolutional Differentiable Logic Gate Networks — HN submission

Tue, 12 Nov 2024 13:04:29 GMT

Convolutional Differentiable Logic Gate Networks

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.