Improved Simulated Annealing in Transiently Chaotic Neural

This paper analyses that the dynamic characteristics of transiently chaotic networks (TCNN) quite sensitively depend on value of the self-feedback connection weights, and researches the annealing function that intensively influences the veracity and search speed of TCNN model. It is proposed an, improved simulated annealing mechanics for value of the self-feedback connection weights that can accelerate the search speed and guarantee the accuracy of the optimal arithmetic. To demonstrate the validity of this mechanics, two examples of function Optimization problems are given.