Generalization over different cellular automata rules learned by a deep feed-forward neural network
Abstract
To test generalization ability of a class of deep neural networks, we randomly generate a large number of different rule sets for 2-D cellular automata (CA), based on John Conway's Game of Life. Using these rules, we compute several trajectories for each CA instance. A deep convolutional encoder-decoder network with short and long range skip connections is trained on various generated CA trajectories to predict the next CA state given its previous states. Results show that the network is able to learn the rules of various, complex cellular automata and generalize to unseen configurations. To some extent, the network shows generalization to rule sets and neighborhood sizes that were not seen during the training at all. Code to reproduce the experiments is publicly available at: https://github.com/SLAMPAI/generalization-cellular-automata
Cite
@article{arxiv.2103.14886,
title = {Generalization over different cellular automata rules learned by a deep feed-forward neural network},
author = {Marcel Aach and Jens Henrik Goebbert and Jenia Jitsev},
journal= {arXiv preprint arXiv:2103.14886},
year = {2021}
}
Comments
Accepted at 23rd International Conference on Artificial Intelligence (July 2021, Las Vegas, USA) To appear in: Springer Transactions on Computational Science & Computational Intelligence