文章基本信息

标题：Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded System
本地全文：下载
作者：Luis M. Torres-Treviño ; Angel Rodríguez-Liñán ; Luis González-Estrada 等
期刊名称：Discrete Dynamics in Nature and Society
印刷版ISSN：1026-0226
电子版ISSN：1607-887X
出版年度：2013
卷号：2013
DOI：10.1155/2013/318758
出版社：Hindawi Publishing Corporation
摘要：Artificial Gaussian neurons are very common structures of artificial neural networks like radial basis function. These artificial neurons use a Gaussian activation function that includes two parameters called the center of mass (cm) and sensibility factor (). Changes on these parameters determine the behavior of the neuron. When the neuron has a feedback output, complex chaotic behavior is displayed. This paper presents a study and implementation of this particular neuron. Stability of fixed points, bifurcation diagrams, and Lyapunov exponents help to determine the dynamical nature of the neuron, and its implementation on embedded system illustrates preliminary results toward embedded chaos computation.