Cellular Automata as Convolutional Neural Networks

Re:Cellular Automata as Convolutional Neural Networks by hardmath123 on Thursday August 13, 2020 @01:34AM (#24140241)

See also: "learning" Conway's Game of Life configurations by gradient descent.

https://hardmath123.github.io/conways-gradient.html

[ Parent | on HN ]

Re:Cellular Automata as Convolutional Neural Networks by dumb1224 on Thursday August 13, 2020 @06:08AM (#24141688)

I wonder if it is because using backpropagation all non-linear functions are chained together when the weights are learnt? Is it naive to think by that formulation the results will be quite similar since the final model equations are close?

[ Parent | on HN ]

Re:Cellular Automata as Convolutional Neural Networks by montebicyclelo on Thursday August 13, 2020 @05:03AM (#24141321)

Excellent write up. I've coincidentally been experimenting with the same thing. Any idea whether this approach could be used to speed up a search for exact solutions?

[ Parent | on HN ]