Error correcting capability of cellular automata based associative memory

Abstract

This paper reports the error correcting capability of an associative memory model built around the sparse network of cellular automata (CA). Analytical formulation supported by experimental results has demonstrated the capability of CA based sparse network to memorize unbiased patterns while accommodating noise. The desired CA are evolved with an efficient formulation of simulated annealing (SA) program. The simple, regular, modular, and cascadable structure of CA based associative memory suits ideally for design of low cost high speed online pattern recognizing machine with the currently available VLSI technology.

Non-uniform cellular automata based associative memory: Evolutionary design and basins of attraction

“…A GMACA is a non-uniform (hybrid) CA (different rules applied to different cells) and can efficiently model an associative memory [9,10,17] to perform pattern recognition task. Fig.…”

“…The design of CA based model for pattern recognition is reported in [3,19,20,22,25]. The search for associative memory model for pattern recognition around simple structure of CAs has been reported in [9,10,17]. The results reported in [9,10,17] have explored the potential application of 3-neighborhood non-uniform CAs, referred to as generalized multiple attractor CAs (GMACAs), as an efficient pattern recognizer.…”

“…The search for associative memory model for pattern recognition around simple structure of CAs has been reported in [9,10,17]. The results reported in [9,10,17] have explored the potential application of 3-neighborhood non-uniform CAs, referred to as generalized multiple attractor CAs (GMACAs), as an efficient pattern recognizer. In [17], the error correcting capability of the GMACAs at single bit noise has been reported considering the attractor cycle of the GMACAs with single or multiple nodes.…”

“…The results reported in [9,10,17] have explored the potential application of 3-neighborhood non-uniform CAs, referred to as generalized multiple attractor CAs (GMACAs), as an efficient pattern recognizer. In [17], the error correcting capability of the GMACAs at single bit noise has been reported considering the attractor cycle of the GMACAs with single or multiple nodes. Also, the simulated annealing program has been used to synthesize the desired GMACA based associative memory [17].…”

“…In [17], the error correcting capability of the GMACAs at single bit noise has been reported considering the attractor cycle of the GMACAs with single or multiple nodes. Also, the simulated annealing program has been used to synthesize the desired GMACA based associative memory [17]. However, these preliminary works have not addressed the following aspects:…”