Tri-state neural network and analysis of its performance

P. G. Madhavan; B. E. Stephens; W. C. Low

doi:10.1080/10798587.1995.10750632

Tri-state neural network and analysis of its performance

P. G. Madhavan, B. E. Stephens, W. C. Low

Neurosurgery

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

The tri-state neuron is introduced to simulate the tri-state property of neurons in the nervous system. The double sigmoid function is utilized as the activation function of the tri-state neural network. The convergence rate and the generalization ability of the tri-state network are compared with those of the traditional bi-state network with single sigmoid function. It is shown analytically and computationally that (1) the tri-state network has a faster convergence rate than the bi-state network and that (2) the generalization ability of these two networks are comparable.

Original language	English (US)
Pages (from-to)	235-246
Number of pages	12
Journal	Intelligent Automation and Soft Computing
Volume	1
Issue number	3
DOIs	https://doi.org/10.1080/10798587.1995.10750632
State	Published - 1995

Bibliographical note

Funding Information:
The authors would like to acknowledge the valuable contribution of Bo Xu at various stages of this research project. Support of this work by IUPUI Research Investment Fund is gratefully acknowledged. We would also like to acknowledge the useful suggestions of one of the anonymous reviewers.

Keywords

Double sigmoid
Fast convergence
Prediction
Tri-state neuron
Volterra time series

Access

10.1080/10798587.1995.10750632

OpenUrl availability

Full text

Cite this

@article{63d4c5a0f7b9494ea4ab6944ae234b2d,

title = "Tri-state neural network and analysis of its performance",

abstract = "The tri-state neuron is introduced to simulate the tri-state property of neurons in the nervous system. The double sigmoid function is utilized as the activation function of the tri-state neural network. The convergence rate and the generalization ability of the tri-state network are compared with those of the traditional bi-state network with single sigmoid function. It is shown analytically and computationally that (1) the tri-state network has a faster convergence rate than the bi-state network and that (2) the generalization ability of these two networks are comparable.",

keywords = "Double sigmoid, Fast convergence, Prediction, Tri-state neuron, Volterra time series",

author = "Madhavan, {P. G.} and Stephens, {B. E.} and Low, {W. C.}",

note = "Funding Information: The authors would like to acknowledge the valuable contribution of Bo Xu at various stages of this research project. Support of this work by IUPUI Research Investment Fund is gratefully acknowledged. We would also like to acknowledge the useful suggestions of one of the anonymous reviewers.",

year = "1995",

doi = "10.1080/10798587.1995.10750632",

language = "English (US)",

volume = "1",

pages = "235--246",

journal = "Intelligent Automation and Soft Computing",

issn = "1079-8587",

publisher = "AutoSoft Press",

number = "3",

}

TY - JOUR

T1 - Tri-state neural network and analysis of its performance

AU - Madhavan, P. G.

AU - Stephens, B. E.

AU - Low, W. C.

N1 - Funding Information: The authors would like to acknowledge the valuable contribution of Bo Xu at various stages of this research project. Support of this work by IUPUI Research Investment Fund is gratefully acknowledged. We would also like to acknowledge the useful suggestions of one of the anonymous reviewers.

PY - 1995

Y1 - 1995

N2 - The tri-state neuron is introduced to simulate the tri-state property of neurons in the nervous system. The double sigmoid function is utilized as the activation function of the tri-state neural network. The convergence rate and the generalization ability of the tri-state network are compared with those of the traditional bi-state network with single sigmoid function. It is shown analytically and computationally that (1) the tri-state network has a faster convergence rate than the bi-state network and that (2) the generalization ability of these two networks are comparable.

AB - The tri-state neuron is introduced to simulate the tri-state property of neurons in the nervous system. The double sigmoid function is utilized as the activation function of the tri-state neural network. The convergence rate and the generalization ability of the tri-state network are compared with those of the traditional bi-state network with single sigmoid function. It is shown analytically and computationally that (1) the tri-state network has a faster convergence rate than the bi-state network and that (2) the generalization ability of these two networks are comparable.

KW - Double sigmoid

KW - Fast convergence

KW - Prediction

KW - Tri-state neuron

KW - Volterra time series

UR - http://www.scopus.com/inward/record.url?scp=77958527404&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77958527404&partnerID=8YFLogxK

U2 - 10.1080/10798587.1995.10750632

DO - 10.1080/10798587.1995.10750632

M3 - Article

AN - SCOPUS:77958527404

SN - 1079-8587

VL - 1

SP - 235

EP - 246

JO - Intelligent Automation and Soft Computing

JF - Intelligent Automation and Soft Computing

IS - 3

ER -

Tri-state neural network and analysis of its performance

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this