EvoDynamic: a framework for the evolution of generally represented dynamical systems and its application to self-organized criticality

EasyChair Preprint 1369

Abstract

Dynamical systems possess a computational capacity which may be exploited in a reservoir computing paradigm. This paper presents a general representation of dynamical systems as an artificial neural network (ANN). Initially, we implement the simplest dynamical system, a cellular automaton. The mathematical fundamentals behind an ANN are maintained, but the weights of the connections and the activation function are adjusted to work as an update rule in the context of cellular automata. The advantages of such implementation are its usage on specialized and optimized deep learning libraries, the capabilities to generalize it to other types of networks and the possibility to evolve cellular automata and other dynamical systems in terms of connectivity, update and learning rules. Our implementation of cellular automata constitutes an initial step towards a more general framework for dynamical systems. Our objective is to evolve such systems with the goal of optimizing their usage in reservoir computing and to model physical computing substrates. Furthermore, we present encouraging preliminary results toward the evolution of complex behavior and self-organized criticality in stochastic elementary cellular automata.

Keyphrases: Reservoir Computing, cellular automata, dynamical systems, evolution, implementation, self-organized criticality

@booklet{EasyChair:1369,
  author    = {Sidney Pontes-Filho and Pedro Lind and Anis Yazidi and Jianhua Zhang and Hugo Hammer and Gustavo B. M. Mello and Ioanna Sandvig and Gunnar Tufte and Stefano Nichele},
  title     = {EvoDynamic: a framework for the evolution of generally represented dynamical systems and its application to self-organized criticality},
  howpublished = {EasyChair Preprint 1369},
  year      = {EasyChair, 2019}}