Adaptive neural network ensemble that learns from imperfect supervisor

P. Hartono; S. Hashimoto

doi:10.1109/ICONIP.2002.1201957

Adaptive neural network ensemble that learns from imperfect supervisor

P. Hartono, S. Hashimoto

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

5 Citations (Scopus)

Abstract

In training supervised-type neural networks, the quality of the training data is one of the most important factors in deciding the quality of the neural networks. Unfortunately, in real world problems, error-free training data are not always easy to obtain. For complex data, it is always possible that erroneous training samples are included, causing to decrease the performance of the neural networks. In this research, we propose a model of neural network ensemble that, through a competition mechanism, has an ability to automatically train one of its members to learn only from the correct training patterns, thus minimizing the effect of the imperfect data.

Original language	English
Title of host publication	ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2561-2565
Number of pages	5
Volume	5
ISBN (Electronic)	9810475241, 9789810475246
DOIs	https://doi.org/10.1109/ICONIP.2002.1201957
Publication status	Published - 2002
Event	9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore Duration: 2002 Nov 18 → 2002 Nov 22

Other

Other	9th International Conference on Neural Information Processing, ICONIP 2002
Country/Territory	Singapore
City	Singapore
Period	02/11/18 → 02/11/22

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Access to Document

10.1109/ICONIP.2002.1201957

Cite this

Hartono, P., & Hashimoto, S. (2002). Adaptive neural network ensemble that learns from imperfect supervisor. In ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age (Vol. 5, pp. 2561-2565). [1201957] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICONIP.2002.1201957

Adaptive neural network ensemble that learns from imperfect supervisor. / Hartono, P.; Hashimoto, S.

ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. Vol. 5 Institute of Electrical and Electronics Engineers Inc., 2002. p. 2561-2565 1201957.

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

Hartono, P & Hashimoto, S 2002, Adaptive neural network ensemble that learns from imperfect supervisor. in ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. vol. 5, 1201957, Institute of Electrical and Electronics Engineers Inc., pp. 2561-2565, 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, Singapore, 02/11/18. https://doi.org/10.1109/ICONIP.2002.1201957

@inproceedings{f5321614258a421abf7673546c9ef149,

title = "Adaptive neural network ensemble that learns from imperfect supervisor",

abstract = "In training supervised-type neural networks, the quality of the training data is one of the most important factors in deciding the quality of the neural networks. Unfortunately, in real world problems, error-free training data are not always easy to obtain. For complex data, it is always possible that erroneous training samples are included, causing to decrease the performance of the neural networks. In this research, we propose a model of neural network ensemble that, through a competition mechanism, has an ability to automatically train one of its members to learn only from the correct training patterns, thus minimizing the effect of the imperfect data.",

author = "P. Hartono and S. Hashimoto",

year = "2002",

doi = "10.1109/ICONIP.2002.1201957",

language = "English",

volume = "5",

pages = "2561--2565",

booktitle = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age",

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

address = "United States",

note = "9th International Conference on Neural Information Processing, ICONIP 2002 ; Conference date: 18-11-2002 Through 22-11-2002",

}

TY - GEN

T1 - Adaptive neural network ensemble that learns from imperfect supervisor

AU - Hartono, P.

AU - Hashimoto, S.

PY - 2002

Y1 - 2002

N2 - In training supervised-type neural networks, the quality of the training data is one of the most important factors in deciding the quality of the neural networks. Unfortunately, in real world problems, error-free training data are not always easy to obtain. For complex data, it is always possible that erroneous training samples are included, causing to decrease the performance of the neural networks. In this research, we propose a model of neural network ensemble that, through a competition mechanism, has an ability to automatically train one of its members to learn only from the correct training patterns, thus minimizing the effect of the imperfect data.

AB - In training supervised-type neural networks, the quality of the training data is one of the most important factors in deciding the quality of the neural networks. Unfortunately, in real world problems, error-free training data are not always easy to obtain. For complex data, it is always possible that erroneous training samples are included, causing to decrease the performance of the neural networks. In this research, we propose a model of neural network ensemble that, through a competition mechanism, has an ability to automatically train one of its members to learn only from the correct training patterns, thus minimizing the effect of the imperfect data.

UR - http://www.scopus.com/inward/record.url?scp=33750599270&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750599270&partnerID=8YFLogxK

U2 - 10.1109/ICONIP.2002.1201957

DO - 10.1109/ICONIP.2002.1201957

M3 - Conference contribution

AN - SCOPUS:33750599270

VL - 5

SP - 2561

EP - 2565

BT - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Conference on Neural Information Processing, ICONIP 2002

Y2 - 18 November 2002 through 22 November 2002

ER -

Adaptive neural network ensemble that learns from imperfect supervisor

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this