Novel chaotic neural network and its application

We give a novel chaotic neuron model whose activation function is composed of Gauss and Sigmoid function. It is shown that the model may exhibit a complex dynamic behavior. The most significant bifurcation processes, leading to chaos, are investigated through the computation of the Lyapunov exponents. Based on this neuron model, we propose a novel chaotic neural network, which realizes simulated chaotic anneal by decaying two parameters simultaneously. Transforming the feature points matching problem into the optimization problem, the network can complete the function of the object recognition. The simulation results prove the validity of the algorithm.