Penalized learning as multiple object optimization

Yasuo Matsuyama, Haruo Nakayama, Taketoshi Sasai, Yuh Perng Chen

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

Abstract

Learning algorithms guided by costs with a variety of penalties are discussed. Both unsupervised and supervised cases are addressed. The penalties are added and/or multiplied to the basic error measure. Since these extra penalties include combination parameters with respect to the basic error, the total problem belongs to a class of multiple object optimization. Learning algorithms on general cases are derived first. Then, individual cases such as penalties on undesirable weights and outputs are treated. A method to find a preferred solution among the Pareto optimal set of the multiple object optimization is given.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages187-192
Number of pages6
Volume1
Publication statusPublished - 1994
Externally publishedYes
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: 1994 Jun 271994 Jun 29

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period94/6/2794/6/29

Fingerprint

Learning algorithms
Costs

ASJC Scopus subject areas

  • Software

Cite this

Matsuyama, Y., Nakayama, H., Sasai, T., & Chen, Y. P. (1994). Penalized learning as multiple object optimization. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 1, pp. 187-192). Piscataway, NJ, United States: IEEE.

Penalized learning as multiple object optimization. / Matsuyama, Yasuo; Nakayama, Haruo; Sasai, Taketoshi; Chen, Yuh Perng.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1 Piscataway, NJ, United States : IEEE, 1994. p. 187-192.

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

Matsuyama, Y, Nakayama, H, Sasai, T & Chen, YP 1994, Penalized learning as multiple object optimization. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 1, IEEE, Piscataway, NJ, United States, pp. 187-192, Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, 94/6/27.
Matsuyama Y, Nakayama H, Sasai T, Chen YP. Penalized learning as multiple object optimization. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1. Piscataway, NJ, United States: IEEE. 1994. p. 187-192
Matsuyama, Yasuo ; Nakayama, Haruo ; Sasai, Taketoshi ; Chen, Yuh Perng. / Penalized learning as multiple object optimization. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1 Piscataway, NJ, United States : IEEE, 1994. pp. 187-192
@inproceedings{5ceedaf02b8147c3b2664c881eb0b069,
title = "Penalized learning as multiple object optimization",
abstract = "Learning algorithms guided by costs with a variety of penalties are discussed. Both unsupervised and supervised cases are addressed. The penalties are added and/or multiplied to the basic error measure. Since these extra penalties include combination parameters with respect to the basic error, the total problem belongs to a class of multiple object optimization. Learning algorithms on general cases are derived first. Then, individual cases such as penalties on undesirable weights and outputs are treated. A method to find a preferred solution among the Pareto optimal set of the multiple object optimization is given.",
author = "Yasuo Matsuyama and Haruo Nakayama and Taketoshi Sasai and Chen, {Yuh Perng}",
year = "1994",
language = "English",
volume = "1",
pages = "187--192",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Penalized learning as multiple object optimization

AU - Matsuyama, Yasuo

AU - Nakayama, Haruo

AU - Sasai, Taketoshi

AU - Chen, Yuh Perng

PY - 1994

Y1 - 1994

N2 - Learning algorithms guided by costs with a variety of penalties are discussed. Both unsupervised and supervised cases are addressed. The penalties are added and/or multiplied to the basic error measure. Since these extra penalties include combination parameters with respect to the basic error, the total problem belongs to a class of multiple object optimization. Learning algorithms on general cases are derived first. Then, individual cases such as penalties on undesirable weights and outputs are treated. A method to find a preferred solution among the Pareto optimal set of the multiple object optimization is given.

AB - Learning algorithms guided by costs with a variety of penalties are discussed. Both unsupervised and supervised cases are addressed. The penalties are added and/or multiplied to the basic error measure. Since these extra penalties include combination parameters with respect to the basic error, the total problem belongs to a class of multiple object optimization. Learning algorithms on general cases are derived first. Then, individual cases such as penalties on undesirable weights and outputs are treated. A method to find a preferred solution among the Pareto optimal set of the multiple object optimization is given.

UR - http://www.scopus.com/inward/record.url?scp=0028739977&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028739977&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028739977

VL - 1

SP - 187

EP - 192

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

CY - Piscataway, NJ, United States

ER -