Gaussian perceptron: Learning algorithms

Taek M Kwon; Michael E. Zervakis

doi:10.1109/ICSMC.1992.271793

Gaussian perceptron: Learning algorithms

Taek M Kwon, Michael E. Zervakis

Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The structure of most neural networks is based on node models with sigmoid-type activation functions. This paper presents a neural network structure whose nodes reflect a Gaussian-type activation function. Three learning algorithms are introduced and compared; the Gaussian perceptron learning (GPL) algorithm, which is based on the conventional perceptron convergence procedure; the least-squares error (LSE) algorithm, which follows the classical steepest descent approach; and the least-log-squares error (LLSE) algorithm, which is a gradient method on a log objective function. In particular, the convergence of the GPL algorithm is proved. The performance on each algorithm is demonstrated through benchmark problems.

Original language	English (US)
Title of host publication	1992 IEEE International Conference on Systems, Man, and Cybernetics
Subtitle of host publication	Emergent Innovations in Information Transfer Processing and Decision Making, SMC 1992
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	105-110
Number of pages	6
ISBN (Electronic)	0780307208, 9780780307209
DOIs	https://doi.org/10.1109/ICSMC.1992.271793
State	Published - Jan 1 1992
Event	IEEE International Conference on Systems, Man, and Cybernetics, SMC 1992 - Chicago, United States Duration: Oct 18 1992 → Oct 21 1992

Publication series

Name	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume	1992-January
ISSN (Print)	1062-922X

Other

Other	IEEE International Conference on Systems, Man, and Cybernetics, SMC 1992
Country	United States
City	Chicago
Period	10/18/92 → 10/21/92

Access

10.1109/ICSMC.1992.271793

Fingerprint Dive into the research topics of 'Gaussian perceptron: Learning algorithms'. Together they form a unique fingerprint.

Cite this

Kwon, T. M., & Zervakis, M. E. (1992). Gaussian perceptron: Learning algorithms. In 1992 IEEE International Conference on Systems, Man, and Cybernetics: Emergent Innovations in Information Transfer Processing and Decision Making, SMC 1992 (pp. 105-110). [271793] (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics; Vol. 1992-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSMC.1992.271793

Gaussian perceptron : Learning algorithms. / Kwon, Taek M; Zervakis, Michael E.

1992 IEEE International Conference on Systems, Man, and Cybernetics: Emergent Innovations in Information Transfer Processing and Decision Making, SMC 1992. Institute of Electrical and Electronics Engineers Inc., 1992. p. 105-110 271793 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics; Vol. 1992-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kwon, TM & Zervakis, ME 1992, Gaussian perceptron: Learning algorithms. in 1992 IEEE International Conference on Systems, Man, and Cybernetics: Emergent Innovations in Information Transfer Processing and Decision Making, SMC 1992., 271793, Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, vol. 1992-January, Institute of Electrical and Electronics Engineers Inc., pp. 105-110, IEEE International Conference on Systems, Man, and Cybernetics, SMC 1992, Chicago, United States, 10/18/92. https://doi.org/10.1109/ICSMC.1992.271793

Kwon TM, Zervakis ME. Gaussian perceptron: Learning algorithms. In 1992 IEEE International Conference on Systems, Man, and Cybernetics: Emergent Innovations in Information Transfer Processing and Decision Making, SMC 1992. Institute of Electrical and Electronics Engineers Inc. 1992. p. 105-110. 271793. (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). https://doi.org/10.1109/ICSMC.1992.271793

Kwon, Taek M ; Zervakis, Michael E. / Gaussian perceptron : Learning algorithms. 1992 IEEE International Conference on Systems, Man, and Cybernetics: Emergent Innovations in Information Transfer Processing and Decision Making, SMC 1992. Institute of Electrical and Electronics Engineers Inc., 1992. pp. 105-110 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).

@inproceedings{7a8e6ef09820415e814a824df1272120,

title = "Gaussian perceptron: Learning algorithms",

abstract = "The structure of most neural networks is based on node models with sigmoid-type activation functions. This paper presents a neural network structure whose nodes reflect a Gaussian-type activation function. Three learning algorithms are introduced and compared; the Gaussian perceptron learning (GPL) algorithm, which is based on the conventional perceptron convergence procedure; the least-squares error (LSE) algorithm, which follows the classical steepest descent approach; and the least-log-squares error (LLSE) algorithm, which is a gradient method on a log objective function. In particular, the convergence of the GPL algorithm is proved. The performance on each algorithm is demonstrated through benchmark problems.",

author = "Kwon, {Taek M} and Zervakis, {Michael E.}",

year = "1992",

month = jan,

day = "1",

doi = "10.1109/ICSMC.1992.271793",

language = "English (US)",

series = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "105--110",

booktitle = "1992 IEEE International Conference on Systems, Man, and Cybernetics",

note = "IEEE International Conference on Systems, Man, and Cybernetics, SMC 1992 ; Conference date: 18-10-1992 Through 21-10-1992",

}

TY - GEN

T1 - Gaussian perceptron

T2 - IEEE International Conference on Systems, Man, and Cybernetics, SMC 1992

AU - Kwon, Taek M

AU - Zervakis, Michael E.

PY - 1992/1/1

Y1 - 1992/1/1

N2 - The structure of most neural networks is based on node models with sigmoid-type activation functions. This paper presents a neural network structure whose nodes reflect a Gaussian-type activation function. Three learning algorithms are introduced and compared; the Gaussian perceptron learning (GPL) algorithm, which is based on the conventional perceptron convergence procedure; the least-squares error (LSE) algorithm, which follows the classical steepest descent approach; and the least-log-squares error (LLSE) algorithm, which is a gradient method on a log objective function. In particular, the convergence of the GPL algorithm is proved. The performance on each algorithm is demonstrated through benchmark problems.

AB - The structure of most neural networks is based on node models with sigmoid-type activation functions. This paper presents a neural network structure whose nodes reflect a Gaussian-type activation function. Three learning algorithms are introduced and compared; the Gaussian perceptron learning (GPL) algorithm, which is based on the conventional perceptron convergence procedure; the least-squares error (LSE) algorithm, which follows the classical steepest descent approach; and the least-log-squares error (LLSE) algorithm, which is a gradient method on a log objective function. In particular, the convergence of the GPL algorithm is proved. The performance on each algorithm is demonstrated through benchmark problems.

UR - http://www.scopus.com/inward/record.url?scp=84960445265&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960445265&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.1992.271793

DO - 10.1109/ICSMC.1992.271793

M3 - Conference contribution

AN - SCOPUS:84960445265

T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

SP - 105

EP - 110

BT - 1992 IEEE International Conference on Systems, Man, and Cybernetics

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 18 October 1992 through 21 October 1992

ER -

Gaussian perceptron: Learning algorithms

Abstract

Publication series

Other

Access

Other files and links

Cite this