Single Gaussian chaotic neuron: numerical study and implementation in an embedded system

DOI10.1155/2013/318758MaRDI QIDQ1956033zbMATH OpenOpenAlexWikidataFDO

Authors L. M. Torres-Treviño, Angel Rodríguez-Liñán, Luis González-Estrada, Gustavo González-Sanmiguel

Publication date 13 June 2013

Published in Discrete Dynamics in Nature and Society (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1155/2013/318758

zbMATH Keywords

artificial Gaussian neuronsembedded chaos computationGaussian activation function

Mathematics Subject Classification ID

Chaos control for problems involving ordinary differential equations (34H10) Strange attractors, chaotic dynamics of systems with hyperbolic behavior (37D45) Dynamical systems in control (37N35) Neural networks for/in biological studies, artificial life and related topics (92B20) Application models in control theory (93C95)

Review text

Summary: 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 (\(\lambda\)). 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.

Recommendations

• A novel delayed chaotic neural model and its circuitry implementation
• Computational abilities of a chaotic neural network
• CHAOTIFICATION OF DISCRETE-TIME SYSTEMS USING NEURONS
• An artificial chaotic spiking neuron inspired by spiral ganglion cell: paralleled spike encoding, theoretical analysis, and electronic circuit implementation
• scientific article; zbMATH DE number 2069459

Cites work

• A method for Lyapunov spectrum estimation using cloned dynamics and its application to the discontinuously-excited FitzHugh-Nagumo model
• Attractors generated from switching unstable dissipative systems
• Coexisting chaotic attractors in a single neuron model with adapting feedback synapse
• Determining Lyapunov exponents from a time series
• Dynamical Systems with Applications using Maple¿
• scientific article; zbMATH DE number 1232237 (Why is no real title available?)
• LOCAL ACTIVITY CRITERIA FOR DISCRETE-MAP CNN
• Multiscroll attractors by switching systems
• Ring-shaped quasisoliton solutions of the circular symmetric 2D sine-Gordon equation

This page was built for publication: Single Gaussian chaotic neuron: numerical study and implementation in an embedded system

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1956033)