Generalization over different cellular automata rules learned by a deep feed-forward neural network
This work addresses generalization challenges in deep learning for computational modeling, though it is incremental as it builds on existing neural network architectures applied to a new domain.
The authors tackled the problem of testing generalization in deep neural networks by training a convolutional encoder-decoder on randomly generated cellular automata rules, and found that the network could learn complex rules and generalize to unseen configurations, including some unseen rule sets and neighborhood sizes.
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