| SLF混沌神经网络及其应用 |
| |
| 引用本文： | 叶永刚,徐耀群. SLF混沌神经网络及其应用[J]. 计算机工程与应用, 2015, 51(21): 74-79 |
| |
| 作者姓名： | 叶永刚 徐耀群 |
| |
| 作者单位： | 1.哈尔滨商业大学 基础科学学院，哈尔滨 1500282.哈尔滨商业大学 系统工程研究所，哈尔滨 150028 |
| |
| 摘 要： | 针对混沌神经网络的单调激励函数，引入Legendre函数和Sigmoid函数组合作为非单调激励函数，构造了一种新的暂态混沌神经元模型（SLF模型），并给出了此混沌神经元的倒分岔图和最大Lyapunov指数时间演化图，利用该模型构建了一种暂态混沌神经网络，通过对非线性函数优化和TSP问题的求解验证了该模型的有效性。
|
| 关 键 词： | 混沌神经网络 Sigmoid函数 Legendre函数 旅行商问题（TSP） Lyapunov指数 |
SLF chaotic neural network model and its application |
| |
| YE Yonggang,XU Yaoqun. SLF chaotic neural network model and its application[J]. Computer Engineering and Applications, 2015, 51(21): 74-79 |
| |
| Authors: | YE Yonggang XU Yaoqun |
| |
| Affiliation: | 1.School of Basic Science, Harbin University of Commerce, Harbin 150028, China2.Institute of System Engineering, Harbin University of Commerce, Harbin 150028, China |
| |
| Abstract: | As to the monotonous activation function of chaotic neural network （SLF model）, it presents a novel transient chaotic-neuron model by introducing the Legendre function and the Sigmoid activation function to compose the non-monotonous activation function. The reversed bifurcation and the maximum Lyapunov exponent of the chaotic neuron are given and the dynamic system is analyzed. Based on the neuron model, a novel transient chaotic-neural network is proposed and applied to non-linear function-optimization and TSP problems. The simulation result indicates the validity of this novel transient chaotic-neural network. |
| |
| Keywords: | chaotic neural network Sigmoid function Legendre function Travelling Salesman Problem（TSP） Lyapunov exponent |
|
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
