Evolving Cellular Automata Based Associative Memory for Pattern Recognition

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 eÆcient scheme to ensure fast convergence of GA is also reported. Experimental results con rm the fact that the GMACA based pattern recognizer is more powerful than the Hop eld network for memorizing arbitrary patterns.