Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded System

Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded System

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 (λ). Changes on these parameters determine t...

Full description

Bibliographic Details
Main Authors: Luis M. Torres-Treviño, Angel Rodríguez-Liñán, Luis González-Estrada, Gustavo González-Sanmiguel
Format: Article
Language:English
Published: Hindawi Limited 2013-01-01
Series:Discrete Dynamics in Nature and Society
Online Access:http://dx.doi.org/10.1155/2013/318758
id doaj-1ca0f9dfa6ac41d08e22e288505fefaa
record_format Article
spelling doaj-1ca0f9dfa6ac41d08e22e288505fefaa2020-11-25T00:10:43ZengHindawi LimitedDiscrete Dynamics in Nature and Society1026-02261607-887X2013-01-01201310.1155/2013/318758318758Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded SystemLuis M. Torres-Treviño0Angel Rodríguez-Liñán1Luis González-Estrada2Gustavo González-Sanmiguel3Universidad Autónoma de Nuevo León, UANL, FIME, Avenida Universidad S/N Ciudad Universitaria, 66451 San Nicolás de los Garza Nuevo León, NL, MexicoUniversidad Autónoma de Nuevo León, UANL, FIME, Avenida Universidad S/N Ciudad Universitaria, 66451 San Nicolás de los Garza Nuevo León, NL, MexicoUniversidad Autónoma de Nuevo León, UANL, FIME, Avenida Universidad S/N Ciudad Universitaria, 66451 San Nicolás de los Garza Nuevo León, NL, MexicoUniversidad Autónoma de Nuevo León, UANL, FIME, Avenida Universidad S/N Ciudad Universitaria, 66451 San Nicolás de los Garza Nuevo León, NL, MexicoArtificial 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 (λ). 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.http://dx.doi.org/10.1155/2013/318758
collection DOAJ
language English
format Article
sources DOAJ
author Luis M. Torres-Treviño
Angel Rodríguez-Liñán
Luis González-Estrada
Gustavo González-Sanmiguel
spellingShingle Luis M. Torres-Treviño
Angel Rodríguez-Liñán
Luis González-Estrada
Gustavo González-Sanmiguel
Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded System
Discrete Dynamics in Nature and Society
author_facet Luis M. Torres-Treviño
Angel Rodríguez-Liñán
Luis González-Estrada
Gustavo González-Sanmiguel
author_sort Luis M. Torres-Treviño
title Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded System
title_short Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded System
title_full Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded System
title_fullStr Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded System
title_full_unstemmed Single Gaussian Chaotic Neuron: Numerical Study and Implementation in an Embedded System
title_sort single gaussian chaotic neuron: numerical study and implementation in an embedded system
publisher Hindawi Limited
series Discrete Dynamics in Nature and Society
issn 1026-0226
1607-887X
publishDate 2013-01-01
description 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 (λ). 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.
url http://dx.doi.org/10.1155/2013/318758
work_keys_str_mv AT luismtorrestrevino singlegaussianchaoticneuronnumericalstudyandimplementationinanembeddedsystem
AT angelrodriguezlinan singlegaussianchaoticneuronnumericalstudyandimplementationinanembeddedsystem
AT luisgonzalezestrada singlegaussianchaoticneuronnumericalstudyandimplementationinanembeddedsystem
AT gustavogonzalezsanmiguel singlegaussianchaoticneuronnumericalstudyandimplementationinanembeddedsystem
_version_ 1725407483506196480

Similar Items