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

Luis TorresTreviño | Zendy; Angel Rodríguez | Zendy; Luis González-Estrada | Zendy; Gustavo González-Sanmiguel | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

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

Author(s) -

Luis TorresTreviño,

Angel Rodríguez,

Luis González-Estrada,

Gustavo González-Sanmiguel

Publication year - 2013

Publication title -

discrete dynamics in nature and society

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.264

H-Index - 39

eISSN - 1607-887X

pISSN - 1026-0226

DOI - 10.1155/2013/318758

Subject(s) - chaotic , bifurcation , computer science , gaussian , lyapunov exponent , artificial neural network , biological neuron model , stability (learning theory) , activation function , function (biology) , neuron , algorithm , computation , artificial intelligence , mathematics , nonlinear system , machine learning , physics , neuroscience , quantum mechanics , evolutionary biology , biology

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

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research