TSP问题的瞬态混沌神经网络算法

采用具有瞬态混沌特性的神经网络(TCNN)解TSP问题。利用神经元的自抑制反馈产生混沌动态，其遍历性能和随机搜索性能有效地克服了Hopfield神经网络(HNN)极易陷入局部极小的缺陷，同时利用一时变参数控制混沌行为，使网络再经过一个短暂的倍周期倒分岔后逐渐趋于一般的Hopfield神经网络，从而收敛到一个最优或近似最优的稳定平衡点。仿真结果表明，TCNN比HNN具有更强的全局寻优能力和更高的搜索效率。

Method to Solve TSP by Neural network with Transient Chaos

TSP problem is solved by a neural network model with transient chaos (TCNN),compared with Hopfield neural network (HNN),TCNN would not be stuck into local minimum by introducing chaos which is generated by negative self-feedback into HNN. With a time-variant parameter to control the chaos ,TCNN goes through an inverse bifurcation process and gradually approaches to HNN with converges to a stable equilibrium point. Numerical simulation shows that TCNN has higher ability of searching for globally optimal to TSP problem than HNN and higher efficiency of searching .