On design and evaluation of tapped-delay neural network architectures

Claus Svarer; Lars Kai Hansen; Jan Larsen

doi:10.1109/ICNN.1993.298533

On design and evaluation of tapped-delay neural network architectures

Claus Svarer, Lars Kai Hansen, Jan Larsen

Technical University of Denmark

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

643 Downloads (Pure)

Abstract

Pruning and evaluation of tapped-delay neural networks for the sunspot benchmark series are addressed. It is shown that the generalization ability of the networks can be improved by pruning using the optimal brain damage method of Le Cun, Denker and Solla. A stop criterion for the pruning algorithm is formulated using a modified version of Akaike's final prediction error estimate. With the proposed stop criterion, the pruning scheme is shown to produce successful architectures with a high yield

Original language	English
Title of host publication	IEEE International Conference on Neural Networks
Volume	Volume 1
Publisher	IEEE
Publication date	1993
Pages	46-51
ISBN (Print)	07-80-30999-5
DOIs	https://doi.org/10.1109/ICNN.1993.298533
Publication status	Published - 1993
Event	1993 IEEE International Conference on Neural Networks - San Francisco, CA, United States Duration: 28 Mar 1993 → 1 Apr 1993 http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=1059

Conference

Conference	1993 IEEE International Conference on Neural Networks
Country/Territory	United States
City	San Francisco, CA
Period	28/03/1993 → 01/04/1993
Internet address	http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=1059

Bibliographical note

Copyright: 1993 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/ICNN.1993.298533

ClausFinal published version, 458 KB

OpenUrl availability

Full text

Cite this

@inproceedings{56a75055824b41afa9705c910b3488c6,

title = "On design and evaluation of tapped-delay neural network architectures",

abstract = "Pruning and evaluation of tapped-delay neural networks for the sunspot benchmark series are addressed. It is shown that the generalization ability of the networks can be improved by pruning using the optimal brain damage method of Le Cun, Denker and Solla. A stop criterion for the pruning algorithm is formulated using a modified version of Akaike's final prediction error estimate. With the proposed stop criterion, the pruning scheme is shown to produce successful architectures with a high yield",

author = "Claus Svarer and Hansen, {Lars Kai} and Jan Larsen",

note = "Copyright: 1993 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; 1993 IEEE International Conference on Neural Networks ; Conference date: 28-03-1993 Through 01-04-1993",

year = "1993",

doi = "10.1109/ICNN.1993.298533",

language = "English",

isbn = "07-80-30999-5",

volume = "Volume 1",

pages = "46--51",

booktitle = "IEEE International Conference on Neural Networks",

publisher = "IEEE",

address = "United States",

url = "http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=1059",

}

TY - GEN

T1 - On design and evaluation of tapped-delay neural network architectures

AU - Svarer, Claus

AU - Hansen, Lars Kai

AU - Larsen, Jan

N1 - Copyright: 1993 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

PY - 1993

Y1 - 1993

N2 - Pruning and evaluation of tapped-delay neural networks for the sunspot benchmark series are addressed. It is shown that the generalization ability of the networks can be improved by pruning using the optimal brain damage method of Le Cun, Denker and Solla. A stop criterion for the pruning algorithm is formulated using a modified version of Akaike's final prediction error estimate. With the proposed stop criterion, the pruning scheme is shown to produce successful architectures with a high yield

AB - Pruning and evaluation of tapped-delay neural networks for the sunspot benchmark series are addressed. It is shown that the generalization ability of the networks can be improved by pruning using the optimal brain damage method of Le Cun, Denker and Solla. A stop criterion for the pruning algorithm is formulated using a modified version of Akaike's final prediction error estimate. With the proposed stop criterion, the pruning scheme is shown to produce successful architectures with a high yield

U2 - 10.1109/ICNN.1993.298533

DO - 10.1109/ICNN.1993.298533

M3 - Article in proceedings

SN - 07-80-30999-5

VL - Volume 1

SP - 46

EP - 51

BT - IEEE International Conference on Neural Networks

PB - IEEE

T2 - 1993 IEEE International Conference on Neural Networks

Y2 - 28 March 1993 through 1 April 1993

ER -

On design and evaluation of tapped-delay neural network architectures

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this