A Neural Network Model Based on Fuzzy Classification Concept

Cheng I. Kao; Yau Hwang Kuo

doi:10.1109/IJCNN.1992.226901

A Neural Network Model Based on Fuzzy Classification Concept

Cheng I. Kao, Yau Hwang Kuo

Department of Computer Science and Information Engineering

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

5 Citations (Scopus)

Abstract

This paper proposes a Fuzzy-Based Neural Network (FBNN) model, which applies a one pass algorithm. The theory of FBNN model originates from embedding a fuzzy classification concept into a parallel neural network architecture. Conventional neural networks such as backpropagation using energy functions as learning principles suffer from two major drawbacks - local minimum problem and long training time. FBNN, however, has the advantage of fast training, and avoids the local minimum problem. Some experiments and comparisons between FBNN and some other neural network models are also made in this paper. According to the experiment results, FBNN shows stronger reliability on classification with respect to PNN, backpropagation, and linear matching method.

Original language	English
Title of host publication	Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	727-732
Number of pages	6
ISBN (Electronic)	0780305590
DOIs	https://doi.org/10.1109/IJCNN.1992.226901
Publication status	Published - 1992
Event	1992 International Joint Conference on Neural Networks, IJCNN 1992 - Baltimore, United States Duration: 1992 Jun 7 → 1992 Jun 11

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2

Conference

Conference	1992 International Joint Conference on Neural Networks, IJCNN 1992
Country/Territory	United States
City	Baltimore
Period	92-06-07 → 92-06-11

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.1992.226901

Cite this

Kao, C. I., & Kuo, Y. H. (1992). A Neural Network Model Based on Fuzzy Classification Concept. In Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992 (pp. 727-732). (Proceedings of the International Joint Conference on Neural Networks; Vol. 2). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.1992.226901

@inproceedings{b9b4b4ff9d564a04ae4b438cbba62a69,

title = "A Neural Network Model Based on Fuzzy Classification Concept",

abstract = "This paper proposes a Fuzzy-Based Neural Network (FBNN) model, which applies a one pass algorithm. The theory of FBNN model originates from embedding a fuzzy classification concept into a parallel neural network architecture. Conventional neural networks such as backpropagation using energy functions as learning principles suffer from two major drawbacks - local minimum problem and long training time. FBNN, however, has the advantage of fast training, and avoids the local minimum problem. Some experiments and comparisons between FBNN and some other neural network models are also made in this paper. According to the experiment results, FBNN shows stronger reliability on classification with respect to PNN, backpropagation, and linear matching method.",

author = "Kao, {Cheng I.} and Kuo, {Yau Hwang}",

note = "Publisher Copyright: {\textcopyright} 1992 IEEE; 1992 International Joint Conference on Neural Networks, IJCNN 1992 ; Conference date: 07-06-1992 Through 11-06-1992",

year = "1992",

doi = "10.1109/IJCNN.1992.226901",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

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

pages = "727--732",

booktitle = "Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992",

address = "United States",

}

Kao, CI & Kuo, YH 1992, A Neural Network Model Based on Fuzzy Classification Concept. in Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992. Proceedings of the International Joint Conference on Neural Networks, vol. 2, Institute of Electrical and Electronics Engineers Inc., pp. 727-732, 1992 International Joint Conference on Neural Networks, IJCNN 1992, Baltimore, United States, 92-06-07. https://doi.org/10.1109/IJCNN.1992.226901

A Neural Network Model Based on Fuzzy Classification Concept. / Kao, Cheng I.; Kuo, Yau Hwang.
Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992. Institute of Electrical and Electronics Engineers Inc., 1992. p. 727-732 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2).

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

TY - GEN

T1 - A Neural Network Model Based on Fuzzy Classification Concept

AU - Kao, Cheng I.

AU - Kuo, Yau Hwang

PY - 1992

Y1 - 1992

N2 - This paper proposes a Fuzzy-Based Neural Network (FBNN) model, which applies a one pass algorithm. The theory of FBNN model originates from embedding a fuzzy classification concept into a parallel neural network architecture. Conventional neural networks such as backpropagation using energy functions as learning principles suffer from two major drawbacks - local minimum problem and long training time. FBNN, however, has the advantage of fast training, and avoids the local minimum problem. Some experiments and comparisons between FBNN and some other neural network models are also made in this paper. According to the experiment results, FBNN shows stronger reliability on classification with respect to PNN, backpropagation, and linear matching method.

AB - This paper proposes a Fuzzy-Based Neural Network (FBNN) model, which applies a one pass algorithm. The theory of FBNN model originates from embedding a fuzzy classification concept into a parallel neural network architecture. Conventional neural networks such as backpropagation using energy functions as learning principles suffer from two major drawbacks - local minimum problem and long training time. FBNN, however, has the advantage of fast training, and avoids the local minimum problem. Some experiments and comparisons between FBNN and some other neural network models are also made in this paper. According to the experiment results, FBNN shows stronger reliability on classification with respect to PNN, backpropagation, and linear matching method.

UR - http://www.scopus.com/inward/record.url?scp=85065828080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065828080&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.1992.226901

DO - 10.1109/IJCNN.1992.226901

M3 - Conference contribution

AN - SCOPUS:85065828080

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 727

EP - 732

BT - Proceedings - 1992 International Joint Conference on Neural Networks, IJCNN 1992

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1992 International Joint Conference on Neural Networks, IJCNN 1992

Y2 - 7 June 1992 through 11 June 1992

ER -

A Neural Network Model Based on Fuzzy Classification Concept

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this