Complexity reduction of singleton based neuro-fuzzy algorithm

P. Baranyi, Kin fong Lei, Yeung Yam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Citations (Scopus)

Abstract

During the past few years efficient singular value-based complexity reduction tools have been developed to fuzzy logic techniques. This paper introduces a singular value-based reduction method to the generalised type neural network. The method conducts singular value decomposition of the weighting functions defined on the connections among the neurons and generates certain linear combinations of the original weighting functions to form a new connection-net for the complexity reduced neural network.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherIEEE
Pages2503-2508
Number of pages6
Volume4
Publication statusPublished - 2000
Event2000 IEEE International Conference on Systems, Man and Cybernetics - Nashville, TN, USA
Duration: Oct 8 2000Oct 11 2000

Other

Other2000 IEEE International Conference on Systems, Man and Cybernetics
CityNashville, TN, USA
Period10/8/0010/11/00

Fingerprint

Neural networks
Singular value decomposition
Fuzzy logic
Neurons

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Baranyi, P., Lei, K. F., & Yam, Y. (2000). Complexity reduction of singleton based neuro-fuzzy algorithm. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 4, pp. 2503-2508). IEEE.

Complexity reduction of singleton based neuro-fuzzy algorithm. / Baranyi, P.; Lei, Kin fong; Yam, Yeung.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 IEEE, 2000. p. 2503-2508.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Baranyi, P, Lei, KF & Yam, Y 2000, Complexity reduction of singleton based neuro-fuzzy algorithm. in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 4, IEEE, pp. 2503-2508, 2000 IEEE International Conference on Systems, Man and Cybernetics, Nashville, TN, USA, 10/8/00.
Baranyi P, Lei KF, Yam Y. Complexity reduction of singleton based neuro-fuzzy algorithm. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4. IEEE. 2000. p. 2503-2508
Baranyi, P. ; Lei, Kin fong ; Yam, Yeung. / Complexity reduction of singleton based neuro-fuzzy algorithm. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 IEEE, 2000. pp. 2503-2508
@inproceedings{c8532fd16c614d7fb080bff1e14faec7,
title = "Complexity reduction of singleton based neuro-fuzzy algorithm",
abstract = "During the past few years efficient singular value-based complexity reduction tools have been developed to fuzzy logic techniques. This paper introduces a singular value-based reduction method to the generalised type neural network. The method conducts singular value decomposition of the weighting functions defined on the connections among the neurons and generates certain linear combinations of the original weighting functions to form a new connection-net for the complexity reduced neural network.",
author = "P. Baranyi and Lei, {Kin fong} and Yeung Yam",
year = "2000",
language = "English",
volume = "4",
pages = "2503--2508",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Complexity reduction of singleton based neuro-fuzzy algorithm

AU - Baranyi, P.

AU - Lei, Kin fong

AU - Yam, Yeung

PY - 2000

Y1 - 2000

N2 - During the past few years efficient singular value-based complexity reduction tools have been developed to fuzzy logic techniques. This paper introduces a singular value-based reduction method to the generalised type neural network. The method conducts singular value decomposition of the weighting functions defined on the connections among the neurons and generates certain linear combinations of the original weighting functions to form a new connection-net for the complexity reduced neural network.

AB - During the past few years efficient singular value-based complexity reduction tools have been developed to fuzzy logic techniques. This paper introduces a singular value-based reduction method to the generalised type neural network. The method conducts singular value decomposition of the weighting functions defined on the connections among the neurons and generates certain linear combinations of the original weighting functions to form a new connection-net for the complexity reduced neural network.

UR - http://www.scopus.com/inward/record.url?scp=0034505020&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034505020&partnerID=8YFLogxK

M3 - Conference contribution

VL - 4

SP - 2503

EP - 2508

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

ER -