Design of a chaotic neural network for training and retrieval of grayscale and binary patterns

Experimental and theoretical evidence shows that biological system processing behavior has nonlinear and chaotic properties. The ability of emerging various solutions for a problem and the existence of a supervisor to guide this variety to become close to the goal, are the two main properties of a problem solver. In this paper, a chaotic neural network which uses chaotic nodes with the logistic map as activation functions is designed to make the ability of emerging various solutions and an NDRAM is considered as a supervisor to guide these various solutions. The proposed chaotic neural network has better performance in comparison with Hopfield, NDRAM, and L. Zhao et al. ChNN.