Chaotic neural fuzzy associative memory

A chaotic neuron model with the linear saturating activation function is an alyzed. The model accounts for the property of relative refractoriness, tha t is, gradual recovery of responsiveness of a biological neuron after a sti mulus is applied to the neuron. A neural network model composed of chaotic neurons with the linear saturating activation functions, which includes the generalized Brain-State-in-a-Box (gBSB) model as a special case, is propos ed and analyzed. The proposed model is then used to implement associative m emory. The existence and stability of equilibrium points of the model are a nalyzed. Fuzzy logic is used to tune associative memory parameters for the purpose of directing the network trajectory to visit memory patterns with s ought features. Simulation results are presented to illustrate the effectiv eness of the memory retrieval capability.