Optimal strategy for simulated annealing mechanics in transiently chaotic neural networks
暂态混沌神经网络中的模拟退火策略优化

This paper analyzed that the dynamic characteristics of transiently chaotic networks(TCNN) quite sensitively depend on value of the self-feedback connection weights,and researched the annealing function that intensively influences the veracity and search speed of TCNN module.It is proposed an optimal strategy for value of the self-feedback connection weights that can accelerate the search speed and guarantee the assurance of the veracity of the optimal arithmetic.To demonstrate the validity of this optimal strategy,two examples of function optimization are given.