小波尺度退火的迟滞混沌神经网络及其应用

Hysteretic chaotic neural network with wavelet scale annealing and its applications

为了有效地避免网络陷入局部极小点,提出了具有小波尺度退火和迟滞激励函数的混沌神经网络模型。将Gauss小波函数作为网络的自反馈项,利用小波尺度的指数递减实现混沌模拟退火,可使网络表现出更丰富的混沌动力学演化行为,有效地增加了混沌搜索的Lyapunov指数的平均水平。利用统一框架理论分析了网络的优化特性和稳定性。旅行商问题(traveling salesman problem,TSP)和直扩序列码分多址(direct sequence-codedivision multiple access,DS-CDMA)多用户检测器的仿真结果表明,该网络能够找到优化问题的全局最优解,并且具有较好的优化性能。

To prevent the network from being trapped in the local minima effectively,a novel chaotic neural network with scale annealing of wavelet and hysteretic activation function is proposed.Gauss wavelet function is used for the self-feedback of the network,and chaotic simulated annealing is realized by the exponentially decaying wavelet scale,which enable the network to exhibit more abundant chaotic dynamic behavior and enhance the average level of Lyapunov exponents of chaotic search effectively.Both the optimization property and the stability are analyzed by applying the unified framework theory.The simulation results on traveling salesman problem（TSP） and direct sequence-code division multiple access（DS-CDMA） suggest that the network can find global optimal solutions of optimization problems,and it has superior optimization performance.