Enhancing cellular automata by an embedded generalized multi-layer perceptron

Authors:
Giuseppe A. Trunfio
Affiliations:
University of Calabria, Center of High-Performance Computing, Rende (CS), Italy
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Year:
2005

Citing 3
Cited 1

An empirical method for modelling and simulating some complex macroscopic phenomena by cellular automata

Future Generation Computer Systems - Special issue on cellular automata: promise in computational science
Evolutionary programming made faster

IEEE Transactions on Evolutionary Computation
A new evolutionary system for evolving artificial neural networks

IEEE Transactions on Neural Networks

Exploiting spatio–temporal data for the multiobjective optimization of cellular automata models

IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

A hybrid approach combining Cellular Automata (CA) and Artificial Neural Networks (ANNs), capable of providing suitable dynamic simulations of some complex systems, is formalized and tested. The proposed method allows to incorporate in the CA transition function the available a priori knowledge of the interaction rules between the elementary system constituents. In order to effectively describe the remaining unknown local rules, an embedded ANN is exploited. The ANN component of the transition function is designed, on the basis of the available data about the emerging behavior of the system to be simulated, by an evolutionary strategy involving both the architecture and weights.