Improvement of classification accuracy by using enhanced query-based learning neural networks

Shyh Jier Huang, Ching Lien Huang

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

An enhanced query-based learning neural network is proposed for the dynamic security control of power systems. Compared to conventional neural network, the enhanced query-based learning provides a classifier at lower computational cost. This methodology requires asking a partially trained classifier to respond to the questions. The response of the query is then taken to the oracle. An oracle is responsible for providing better quality of training data. The regions of classification ambiguity will thus be narrowed. It can be seen that the proposed method is intrinsically different from learning by randomly generated data. With only a small amount of additional complexity, the enhanced query-based neural network approach greatly increases the classification accuracy of neural networks.

Original languageEnglish
Pages398-402
Number of pages5
Publication statusPublished - 1996 Jan 1
EventProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA
Duration: 1996 Jun 31996 Jun 6

Other

OtherProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
CityWashington, DC, USA
Period96-06-0396-06-06

Fingerprint

Neural networks
Classifiers
Costs

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Huang, S. J., & Huang, C. L. (1996). Improvement of classification accuracy by using enhanced query-based learning neural networks. 398-402. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .
Huang, Shyh Jier ; Huang, Ching Lien. / Improvement of classification accuracy by using enhanced query-based learning neural networks. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .5 p.
@conference{56fcf03969764f858da8820cae991152,
title = "Improvement of classification accuracy by using enhanced query-based learning neural networks",
abstract = "An enhanced query-based learning neural network is proposed for the dynamic security control of power systems. Compared to conventional neural network, the enhanced query-based learning provides a classifier at lower computational cost. This methodology requires asking a partially trained classifier to respond to the questions. The response of the query is then taken to the oracle. An oracle is responsible for providing better quality of training data. The regions of classification ambiguity will thus be narrowed. It can be seen that the proposed method is intrinsically different from learning by randomly generated data. With only a small amount of additional complexity, the enhanced query-based neural network approach greatly increases the classification accuracy of neural networks.",
author = "Huang, {Shyh Jier} and Huang, {Ching Lien}",
year = "1996",
month = "1",
day = "1",
language = "English",
pages = "398--402",
note = "Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) ; Conference date: 03-06-1996 Through 06-06-1996",

}

Huang, SJ & Huang, CL 1996, 'Improvement of classification accuracy by using enhanced query-based learning neural networks', Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, 96-06-03 - 96-06-06 pp. 398-402.

Improvement of classification accuracy by using enhanced query-based learning neural networks. / Huang, Shyh Jier; Huang, Ching Lien.

1996. 398-402 Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Improvement of classification accuracy by using enhanced query-based learning neural networks

AU - Huang, Shyh Jier

AU - Huang, Ching Lien

PY - 1996/1/1

Y1 - 1996/1/1

N2 - An enhanced query-based learning neural network is proposed for the dynamic security control of power systems. Compared to conventional neural network, the enhanced query-based learning provides a classifier at lower computational cost. This methodology requires asking a partially trained classifier to respond to the questions. The response of the query is then taken to the oracle. An oracle is responsible for providing better quality of training data. The regions of classification ambiguity will thus be narrowed. It can be seen that the proposed method is intrinsically different from learning by randomly generated data. With only a small amount of additional complexity, the enhanced query-based neural network approach greatly increases the classification accuracy of neural networks.

AB - An enhanced query-based learning neural network is proposed for the dynamic security control of power systems. Compared to conventional neural network, the enhanced query-based learning provides a classifier at lower computational cost. This methodology requires asking a partially trained classifier to respond to the questions. The response of the query is then taken to the oracle. An oracle is responsible for providing better quality of training data. The regions of classification ambiguity will thus be narrowed. It can be seen that the proposed method is intrinsically different from learning by randomly generated data. With only a small amount of additional complexity, the enhanced query-based neural network approach greatly increases the classification accuracy of neural networks.

UR - http://www.scopus.com/inward/record.url?scp=0029747014&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029747014&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029747014

SP - 398

EP - 402

ER -

Huang SJ, Huang CL. Improvement of classification accuracy by using enhanced query-based learning neural networks. 1996. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .