Design and characterization of cellular automata based associative memory for pattern recognition

Author

Ganguly, Niloy ; Maji, Pradipta ; Sikdar, Biplab K. ; Chaudhuri, P. Pal

Author_Institution

Comput. Centre, IISWBM, Calcutta, India

Volume

34

Issue

1

fYear

2004

Firstpage

672

Lastpage

678

Abstract

This paper reports a cellular automata (CA) based model of associative memory. The model has been evolved around a special class of CA referred to as generalized multiple attractor cellular automata (GMACA). The GMACA based associative memory is designed to address the problem of pattern recognition. Its storage capacity is found to be better than that of Hopfield network. The GMACA are configured with nonlinear CA rules that are evolved through genetic algorithm (GA). Successive generations of GA select the rules at the edge of chaos. The study confirms the potential of GMACA to perform complex computations like pattern recognition at the edge of chaos.

Keywords

Hopfield neural nets; cellular automata; content-addressable storage; genetic algorithms; pattern recognition; Hopfield network; associative memory; generalized multiple attractor cellular automata; genetic algorithm; nonlinear cellular automata rules; pattern recognition; Algorithm design and analysis; Associative memory; Cellular neural networks; Chaos; Genetic algorithms; Neural networks; Pattern matching; Pattern recognition; State-space methods; Storage automation; Algorithms; Animals; Association; Computer Simulation; Humans; Memory; Models, Neurological; Nerve Net; Neural Networks (Computer); Neurons; Pattern Recognition, Automated;

fLanguage

English

Journal_Title

Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

1083-4419

Type

jour

DOI

10.1109/TSMCB.2002.806494

Filename

1262538