Reconstructing cellular automata rules from observations at nonconsecutive times
December 03, 2020 Β· Declared Dead Β· π Physical Review E
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Veit Elser
arXiv ID
2012.02179
Category
nlin.CG
Cross-listed
cs.LG
Citations
4
Venue
Physical Review E
Last Checked
3 months ago
Abstract
Recent experiments by Springer and Kenyon have shown that a deep neural network can be trained to predict the action of $t$ steps of Conway's Game of Life automaton given millions of examples of this action on random initial states. However, training was never completely successful for $t>1$, and even when successful, a reconstruction of the elementary rule ($t=1$) from $t>1$ data is not within the scope of what the neural network can deliver. We describe an alternative network-like method, based on constraint projections, where this is possible. From a single data item this method perfectly reconstructs not just the automaton rule but also the states in the time steps it did not see. For a unique reconstruction, the size of the initial state need only be large enough that it and the $t-1$ states it evolves into contain all possible automaton input patterns. We demonstrate the method on 1D binary cellular automata that take inputs from $n$ adjacent cells. The unknown rules in our experiments are not restricted to simple rules derived from a few linear functions on the inputs (as in Game of Life), but include all $2^{2^n}$ possible rules on $n$ inputs. Our results extend to $n=6$, for which exhaustive rule-search is not feasible. By relaxing translational symmetry in space and also time, our method is attractive as a platform for the learning of binary data, since the discreteness of the variables does not pose the same challenge it does for gradient-based methods.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β nlin.CG
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Lenia - Biology of Artificial Life
R.I.P.
π»
Ghosted
Evolving Structures in Complex Systems
R.I.P.
π»
Ghosted
Implementation of Lenia as a Reaction-Diffusion System
R.I.P.
π»
Ghosted
Self-Reproduction and Evolution in Cellular Automata: 25 Years after Evoloops
R.I.P.
π»
Ghosted
The ideal energy of classical lattice dynamics
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted