Adaptive Regularization of Neural Networks Using Conjugate Gradient

Cyril Goutte; Jan Larsen

doi:10.1109/ICASSP.1998.675486

Adaptive Regularization of Neural Networks Using Conjugate Gradient

Cyril Goutte
, Jan Larsen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

619 Downloads (Orbit)

Abstract

Andersen et al. (1997) and Larsen et al. (1996, 1997) suggested a regularization scheme which iteratively adapts regularization parameters by minimizing validation error using simple gradient descent. In this contribution we present an improved algorithm based on the conjugate gradient technique. Numerical experiments with feedforward neural networks successfully demonstrate improved generalization ability and lower computational cost

Original language	English
Title of host publication	Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Volume	2
Place of Publication	New York
Publisher	IEEE
Publication date	1998
Pages	1201-1204
ISBN (Print)	0-7803-4428-6
DOIs	https://doi.org/10.1109/ICASSP.1998.675486
Publication status	Published - 1998
Event	1998 IEEE International Conference on Acoustics, Speech and Signal Processing - Seattle, United States Duration: 12 May 1998 → 15 May 1998 Conference number: 23

Conference

Conference	1998 IEEE International Conference on Acoustics, Speech and Signal Processing
Number	23
Country/Territory	United States
City	Seattle
Period	12/05/1998 → 15/05/1998

Bibliographical note

Copyright: 1998 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

Access to Document

10.1109/ICASSP.1998.675486

GoutteFinal published version, 378 KB

OpenUrl availability

Full text

Cite this

@inproceedings{6cce399b71534f45bd2f1f86fe6371ae,

title = "Adaptive Regularization of Neural Networks Using Conjugate Gradient",

abstract = "Andersen et al. (1997) and Larsen et al. (1996, 1997) suggested a regularization scheme which iteratively adapts regularization parameters by minimizing validation error using simple gradient descent. In this contribution we present an improved algorithm based on the conjugate gradient technique. Numerical experiments with feedforward neural networks successfully demonstrate improved generalization ability and lower computational cost",

author = "Cyril Goutte and Jan Larsen",

note = "Copyright: 1998 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE; 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998 ; Conference date: 12-05-1998 Through 15-05-1998",

year = "1998",

doi = "10.1109/ICASSP.1998.675486",

language = "English",

isbn = "0-7803-4428-6",

volume = "2",

pages = "1201--1204",

booktitle = "Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on",

publisher = "IEEE",

address = "United States",

}

Goutte, C & Larsen, J 1998, Adaptive Regularization of Neural Networks Using Conjugate Gradient. in Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on. vol. 2, IEEE, New York, pp. 1201-1204, 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, Seattle, Washington, United States, 12/05/1998. https://doi.org/10.1109/ICASSP.1998.675486

TY - GEN

T1 - Adaptive Regularization of Neural Networks Using Conjugate Gradient

AU - Goutte, Cyril

AU - Larsen, Jan

N1 - Conference code: 23

PY - 1998

Y1 - 1998

N2 - Andersen et al. (1997) and Larsen et al. (1996, 1997) suggested a regularization scheme which iteratively adapts regularization parameters by minimizing validation error using simple gradient descent. In this contribution we present an improved algorithm based on the conjugate gradient technique. Numerical experiments with feedforward neural networks successfully demonstrate improved generalization ability and lower computational cost

AB - Andersen et al. (1997) and Larsen et al. (1996, 1997) suggested a regularization scheme which iteratively adapts regularization parameters by minimizing validation error using simple gradient descent. In this contribution we present an improved algorithm based on the conjugate gradient technique. Numerical experiments with feedforward neural networks successfully demonstrate improved generalization ability and lower computational cost

U2 - 10.1109/ICASSP.1998.675486

DO - 10.1109/ICASSP.1998.675486

M3 - Article in proceedings

SN - 0-7803-4428-6

VL - 2

SP - 1201

EP - 1204

BT - Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on

PB - IEEE

CY - New York

T2 - 1998 IEEE International Conference on Acoustics, Speech and Signal Processing

Y2 - 12 May 1998 through 15 May 1998

ER -

Adaptive Regularization of Neural Networks Using Conjugate Gradient

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this