Chaotic dynamics of time-delay neural networks

Jose C. Principe; Pei-Chen Lo

Chaotic dynamics of time-delay neural networks

Jose C. Principe^*, Pei-Chen Lo

^*Corresponding author for this work

Institute of Electrical and Control Engineering

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

A study is made of the nonlinear dynamical properties of a class of recurrent artificial neural networks with time delay that have been proposed in the literature to learn and recognize time-varying input patterns. Their nonlinear dynamics are studied to see if they have the potential to model nonlinear dynamical behavior of biological field potentials such as the electroencephalogram (EEG). It is shown that changing the value of the weights in a periodic fashion causes the output of time-delay neural networks to show a correlation dimension in the EEG range.

Original language	English
Pages	403-409
Number of pages	7
State	Published - 1 Dec 1990
Event	1990 International Joint Conference on Neural Networks - IJCNN 90 Part 3 (of 3) - San Diego, CA, USA Duration: 17 Jun 1990 → 21 Jun 1990

Conference

Conference	1990 International Joint Conference on Neural Networks - IJCNN 90 Part 3 (of 3)
City	San Diego, CA, USA
Period	17/06/90 → 21/06/90

Access to Document

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Chaotic dynamics of time-delay neural networks'. Together they form a unique fingerprint.

Cite this

@conference{e7ce92e8307f47f28344964e99aca704,

title = "Chaotic dynamics of time-delay neural networks",

abstract = "A study is made of the nonlinear dynamical properties of a class of recurrent artificial neural networks with time delay that have been proposed in the literature to learn and recognize time-varying input patterns. Their nonlinear dynamics are studied to see if they have the potential to model nonlinear dynamical behavior of biological field potentials such as the electroencephalogram (EEG). It is shown that changing the value of the weights in a periodic fashion causes the output of time-delay neural networks to show a correlation dimension in the EEG range.",

author = "Principe, {Jose C.} and Pei-Chen Lo",

year = "1990",

month = dec,

day = "1",

language = "English",

pages = "403--409",

note = "null ; Conference date: 17-06-1990 Through 21-06-1990",

}

TY - CONF

T1 - Chaotic dynamics of time-delay neural networks

AU - Principe, Jose C.

AU - Lo, Pei-Chen

PY - 1990/12/1

Y1 - 1990/12/1

N2 - A study is made of the nonlinear dynamical properties of a class of recurrent artificial neural networks with time delay that have been proposed in the literature to learn and recognize time-varying input patterns. Their nonlinear dynamics are studied to see if they have the potential to model nonlinear dynamical behavior of biological field potentials such as the electroencephalogram (EEG). It is shown that changing the value of the weights in a periodic fashion causes the output of time-delay neural networks to show a correlation dimension in the EEG range.

AB - A study is made of the nonlinear dynamical properties of a class of recurrent artificial neural networks with time delay that have been proposed in the literature to learn and recognize time-varying input patterns. Their nonlinear dynamics are studied to see if they have the potential to model nonlinear dynamical behavior of biological field potentials such as the electroencephalogram (EEG). It is shown that changing the value of the weights in a periodic fashion causes the output of time-delay neural networks to show a correlation dimension in the EEG range.

UR - http://www.scopus.com/inward/record.url?scp=0025539360&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0025539360

SP - 403

EP - 409

Y2 - 17 June 1990 through 21 June 1990

ER -