Variable structure control based on-line learning design for continuous time multilayer networks

Francklin Rivas-Echeverria; Eliezer Colina-Morles

Variable structure control based on-line learning design for continuous time multilayer networks

Francklin Rivas-Echeverria^*, Eliezer Colina-Morles

^*Corresponding author for this work

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

2 Scopus citations

Abstract

The purpose of this paper is to introduce Variable Structure-based-on-line learning algorithms for continuous time two layer and three layer perceptron networks with non-linear and linear activation functions. The computer implementation of the proposed algorithms result in a temporal learning capabilities of a neural network with dynamically adjusted weights, and zero convergence of the learning error in a finite time. The performance of the considered networks is tested in terms of solving a tracking problem of a sine signal.

Original language	English
Pages	548-552
Number of pages	5
State	Published - 1996
Externally published	Yes
Event	Proceedings of the 1996 IEEE International Symposium on Intelligent Control - Dearborn, MI, USA Duration: 15 Sep 1996 → 18 Sep 1996

Conference

Conference	Proceedings of the 1996 IEEE International Symposium on Intelligent Control
City	Dearborn, MI, USA
Period	15/09/96 → 18/09/96

Cite this

@conference{156d9e57503546758f3a9695ca6a0e98,

title = "Variable structure control based on-line learning design for continuous time multilayer networks",

abstract = "The purpose of this paper is to introduce Variable Structure-based-on-line learning algorithms for continuous time two layer and three layer perceptron networks with non-linear and linear activation functions. The computer implementation of the proposed algorithms result in a temporal learning capabilities of a neural network with dynamically adjusted weights, and zero convergence of the learning error in a finite time. The performance of the considered networks is tested in terms of solving a tracking problem of a sine signal.",

author = "Francklin Rivas-Echeverria and Eliezer Colina-Morles",

year = "1996",

language = "English",

pages = "548--552",

note = "Proceedings of the 1996 IEEE International Symposium on Intelligent Control ; Conference date: 15-09-1996 Through 18-09-1996",

}

TY - CONF

T1 - Variable structure control based on-line learning design for continuous time multilayer networks

AU - Rivas-Echeverria, Francklin

AU - Colina-Morles, Eliezer

PY - 1996

Y1 - 1996

N2 - The purpose of this paper is to introduce Variable Structure-based-on-line learning algorithms for continuous time two layer and three layer perceptron networks with non-linear and linear activation functions. The computer implementation of the proposed algorithms result in a temporal learning capabilities of a neural network with dynamically adjusted weights, and zero convergence of the learning error in a finite time. The performance of the considered networks is tested in terms of solving a tracking problem of a sine signal.

AB - The purpose of this paper is to introduce Variable Structure-based-on-line learning algorithms for continuous time two layer and three layer perceptron networks with non-linear and linear activation functions. The computer implementation of the proposed algorithms result in a temporal learning capabilities of a neural network with dynamically adjusted weights, and zero convergence of the learning error in a finite time. The performance of the considered networks is tested in terms of solving a tracking problem of a sine signal.

UR - https://www.scopus.com/pages/publications/0030357621

M3 - Paper

AN - SCOPUS:0030357621

SP - 548

EP - 552

T2 - Proceedings of the 1996 IEEE International Symposium on Intelligent Control

Y2 - 15 September 1996 through 18 September 1996

ER -

Variable structure control based on-line learning design for continuous time multilayer networks

Abstract

Conference

Other files and links

Fingerprint

Cite this