Evolving Cellular Automata Based Associative Memory for Pattern Recognition

Authors:
Niloy Ganguly;Arijit Das;Pradipta Maji;Biplab K. Sikdar;Parimal Pal Chaudhuri
Affiliations:
-;-;-;-;-
Venue:
HiPC '01 Proceedings of the 8th International Conference on High Performance Computing
Year:
2001

Citing 4
Cited 4

Transition phenomena is cellular automata rule space

Physica D
Introduction to the theory of neural computation

Introduction to the theory of neural computation
Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Co-evolving non-uniform cellular automata to perform computations

Physica D

Cellular Automata Machine for Pattern Recognition

ACRI '01 Proceedings of the 5th International Conference on Cellular Automata for Research and Industry
Chaotic hopping between attractors in neural networks

Neural Networks
Characterization of Single Cycle CA and its Application in Pattern Classification

Electronic Notes in Theoretical Computer Science (ENTCS)
An improved multiple-attractor cellular automata classifier with a tree frame based on CART

Computers & Mathematics with Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper reports a Cellular Automata (CA) model for pattern recognition. The special class of CA, referred to as GMACA (Generalized Multiple Attractor Cellular Automata), is employed to design the CA based associative memory for pattern recognition. The desired GMACA are evolved through the implementation of genetic algorithm (GA). An efficient scheme to ensure fast convergence of GA is also reported. Experimental results confirm the fact that the GMACA based pattern recognizer is more powerful than the Hopfield network for memorizing arbitrary patterns.