Cellular automata as convolutional neural networks · HackerPapers discussions

Cellular automata as convolutional neural networks — mentioned by friedchips

Tue, 26 Aug 2025 11:53:28 GMT

Yep, see my comment above and especially http://arxiv.org/abs/1809.02942

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

Cellular automata as convolutional neural networks — mentioned by friedchips

Tue, 26 Aug 2025 11:51:32 GMT

I'm not involved in this project, but I partially replicated the results from Mordvintsev et al. a few years ago because I found the idea interesting. The key idea for me was learning the possibly unknown rules of a CA from training examples. This sounded to me like something that could be useful in science, to learn about spatially distributed processes. Or in ML as a new idea for image classification or segmentation. The hope was always that a CA could be learned which would have a simple discrete representation which could then be used in inference with much lower computational needs than…

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

Cellular automata as convolutional neural networks — HN submission

Wed, 12 Aug 2020 11:23:02 GMT

Cellular Automata as Convolutional Neural Networks

87 points; 14 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Cellular automata as convolutional neural networks — HN submission

Sun, 30 Sep 2018 20:31:45 GMT

Cellular automata as convolutional neural networks

83 points; 6 discussion replies on HN. Paper and source history. A submission is not an endorsement.