On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs)

Jing Wang; C. L.Philip Chen; Chi-Hsu Wang

doi:10.1109/ICSMC.2012.6378110

On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs)

Jing Wang^*, C. L.Philip Chen, Chi-Hsu Wang

^*Corresponding author for this work

Department of Electrical and Computer Engineering

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

2 Scopus citations

Abstract

In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent fully connected three layer neural network, or FFNN. Based on the FFNN, conjugate gradients (CG) training algorithm is derived to tune both the premise and consequent part of FNN, and apparently increase the speed of convergence. Illustrative examples are presented to check the validity of the proposed theory and algorithms. Simulation achieves satisfactory results. Developing CG training algorithm for FNN via its equivalent FFNN has its emerging values in all engineering applications using FNN, such as intelligent adaptive control, pattern recognition, and signal processing..., etc.

Original language	English
Title of host publication	Proceedings 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012
Pages	2446-2451
Number of pages	6
DOIs	https://doi.org/10.1109/ICSMC.2012.6378110
State	Published - 1 Dec 2012
Event	2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012 - Seoul, Korea, Republic of Duration: 14 Oct 2012 → 17 Oct 2012

Publication series

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

Conference

Conference	2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012
Country	Korea, Republic of
City	Seoul
Period	14/10/12 → 17/10/12

Keywords

Fuzzy Logic
Fuzzy Neural Networks
Gradient Descent
Neural Networks
conjugate gradients

Access to Document

10.1109/ICSMC.2012.6378110

Link to publication in Scopus

Fingerprint Dive into the research topics of 'On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs)'. Together they form a unique fingerprint.

Cite this

Wang, J., Chen, C. L. P., & Wang, C-H. (2012). On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs). In Proceedings 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012 (pp. 2446-2451). [6378110] (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). https://doi.org/10.1109/ICSMC.2012.6378110

Wang, Jing ; Chen, C. L.Philip ; Wang, Chi-Hsu. / On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs). Proceedings 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012. 2012. pp. 2446-2451 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).

@inproceedings{f3103434c70e41a7b6f7c7576d559b9c,

title = "On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs)",

abstract = "In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent fully connected three layer neural network, or FFNN. Based on the FFNN, conjugate gradients (CG) training algorithm is derived to tune both the premise and consequent part of FNN, and apparently increase the speed of convergence. Illustrative examples are presented to check the validity of the proposed theory and algorithms. Simulation achieves satisfactory results. Developing CG training algorithm for FNN via its equivalent FFNN has its emerging values in all engineering applications using FNN, such as intelligent adaptive control, pattern recognition, and signal processing..., etc.",

keywords = "Fuzzy Logic, Fuzzy Neural Networks, Gradient Descent, Neural Networks, conjugate gradients",

author = "Jing Wang and Chen, {C. L.Philip} and Chi-Hsu Wang",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/ICSMC.2012.6378110",

language = "English",

isbn = "9781467317146",

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

pages = "2446--2451",

booktitle = "Proceedings 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012",

note = "null ; Conference date: 14-10-2012 Through 17-10-2012",

}

Wang, J, Chen, CLP & Wang, C-H 2012, On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs). in Proceedings 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012., 6378110, Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, pp. 2446-2451, 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012, Seoul, Korea, Republic of, 14/10/12. https://doi.org/10.1109/ICSMC.2012.6378110

On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs). / Wang, Jing; Chen, C. L.Philip; Wang, Chi-Hsu.

Proceedings 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012. 2012. p. 2446-2451 6378110 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).

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

TY - GEN

T1 - On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs)

AU - Wang, Jing

AU - Chen, C. L.Philip

AU - Wang, Chi-Hsu

PY - 2012/12/1

Y1 - 2012/12/1

N2 - In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent fully connected three layer neural network, or FFNN. Based on the FFNN, conjugate gradients (CG) training algorithm is derived to tune both the premise and consequent part of FNN, and apparently increase the speed of convergence. Illustrative examples are presented to check the validity of the proposed theory and algorithms. Simulation achieves satisfactory results. Developing CG training algorithm for FNN via its equivalent FFNN has its emerging values in all engineering applications using FNN, such as intelligent adaptive control, pattern recognition, and signal processing..., etc.

AB - In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent fully connected three layer neural network, or FFNN. Based on the FFNN, conjugate gradients (CG) training algorithm is derived to tune both the premise and consequent part of FNN, and apparently increase the speed of convergence. Illustrative examples are presented to check the validity of the proposed theory and algorithms. Simulation achieves satisfactory results. Developing CG training algorithm for FNN via its equivalent FFNN has its emerging values in all engineering applications using FNN, such as intelligent adaptive control, pattern recognition, and signal processing..., etc.

KW - Fuzzy Logic

KW - Fuzzy Neural Networks

KW - Gradient Descent

KW - Neural Networks

KW - conjugate gradients

UR - http://www.scopus.com/inward/record.url?scp=84872417372&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2012.6378110

DO - 10.1109/ICSMC.2012.6378110

M3 - Conference contribution

AN - SCOPUS:84872417372

SN - 9781467317146

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

SP - 2446

EP - 2451

BT - Proceedings 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012

Y2 - 14 October 2012 through 17 October 2012

ER -

Wang J, Chen CLP, Wang C-H. On the conjugate gradients (CG) training algorithm of fuzzy neural networks (FNNs) via its equivalent fully connected neural networks (FFNNs). In Proceedings 2012 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2012. 2012. p. 2446-2451. 6378110. (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). https://doi.org/10.1109/ICSMC.2012.6378110