A CELLULAR NEURAL-NETWORK LEARNING THE PSEUDORANDOM BEHAVIOR OF A COMPLEX SYSTEM

This paper presents the development of a Cellular Neural Network (CNN) architecture that is capable of learning the behaviour of a Cellular Automaton (CA) operating under local rule 30. Such a CA rule models th e complex behaviour of a random system. The CNN was trained using the Levenberg-Marquardt approximation to Newton's method and convergence w as achieved very fast. The proposed CNN was able to generalize efficie ntly and it can be used as a pseudorandom number generator. The CNN ar chitecture proposed in this paper is especially suited to VLSI impleme ntation due to its inherent regularity, modularity and parallelism and also, due to the locality of interconnections.