Implementation of a single chaotic neuron using an embedded system

  • Authors:
  • Luis González-Estrada;Gustavo González-Sanmiguel;Luis Martin Torres-Treviño;Angel Rodríguez

  • Affiliations:
  • FIME, Universidad Autónoma de Nuevo León, San Nicolás de los Garza, N.L., Mexico;FIME, Universidad Autónoma de Nuevo León, San Nicolás de los Garza, N.L., Mexico;FIME, Universidad Autónoma de Nuevo León, San Nicolás de los Garza, N.L., Mexico;FIME, Universidad Autónoma de Nuevo León, San Nicolás de los Garza, N.L., Mexico

  • Venue:
  • MICAI'12 Proceedings of the 11th Mexican international conference on Advances in Computational Intelligence - Volume Part II
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

A single chaotic neuron can be developed using a single neuron with a Gaussian activation function and feeding back the output to its input. The Gaussian activation function has two parameters, the center of mass and the width of the bell called sensibility factor. The change of these parameters determines the behavior of the single neuron that could be stationary but more of the times is dynamic inclusive chaotic. This paper presents an implementation of this single neuron in an embedded system generating a set of bifurcation plots illustrating the dynamic complexity that could have this simple system.