Design and evaluation of neural classifiers

Mads Hintz-Madsen; Morten With Pedersen; Lars Kai Hansen; Jan Larsen

doi:10.1109/NNSP.1996.548352

Design and evaluation of neural classifiers

Mads Hintz-Madsen, Morten With Pedersen, Lars Kai Hansen, Jan Larsen

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

300 Downloads (Pure)

Abstract

In this paper we propose a method for the design of feedforward neural classifiers based on regularization and adaptive architectures. Using a penalized maximum likelihood scheme we derive a modified form of the entropy error measure and an algebraic estimate of the test error. In conjunction with optimal brain damage pruning the test error estimate is used to optimize the network architecture. The scheme is evaluated on an artificial and a real world problem

Original language	English
Title of host publication	Proceedings of the IEEE Signal Processing Society Workshop Neural Networks for Signal Processing
Publisher	IEEE
Publication date	1996
Pages	223-232
ISBN (Print)	07-80-33550-3
DOIs	https://doi.org/10.1109/NNSP.1996.548352
Publication status	Published - 1996
Event	Neural Network for Signal Processing - Kyoto Duration: 1 Jan 1996 → … Conference number: 6th

Conference

Conference	Neural Network for Signal Processing
Number	6th
City	Kyoto
Period	01/01/1996 → …

Bibliographical note

Copyright 1996 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/NNSP.1996.548352

WithFinal published version, 483 KB

OpenUrl availability

Full text

Cite this

@inproceedings{d7719002199a4cec94d17bb5250b256d,

title = "Design and evaluation of neural classifiers",

abstract = "In this paper we propose a method for the design of feedforward neural classifiers based on regularization and adaptive architectures. Using a penalized maximum likelihood scheme we derive a modified form of the entropy error measure and an algebraic estimate of the test error. In conjunction with optimal brain damage pruning the test error estimate is used to optimize the network architecture. The scheme is evaluated on an artificial and a real world problem",

author = "Mads Hintz-Madsen and Pedersen, {Morten With} and Hansen, {Lars Kai} and Jan Larsen",

note = "Copyright 1996 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; Neural Network for Signal Processing ; Conference date: 01-01-1996",

year = "1996",

doi = "10.1109/NNSP.1996.548352",

language = "English",

isbn = "07-80-33550-3",

pages = "223--232",

booktitle = "Proceedings of the IEEE Signal Processing Society Workshop Neural Networks for Signal Processing",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Design and evaluation of neural classifiers

AU - Hintz-Madsen, Mads

AU - Pedersen, Morten With

AU - Hansen, Lars Kai

AU - Larsen, Jan

N1 - Conference code: 6th

PY - 1996

Y1 - 1996

N2 - In this paper we propose a method for the design of feedforward neural classifiers based on regularization and adaptive architectures. Using a penalized maximum likelihood scheme we derive a modified form of the entropy error measure and an algebraic estimate of the test error. In conjunction with optimal brain damage pruning the test error estimate is used to optimize the network architecture. The scheme is evaluated on an artificial and a real world problem

AB - In this paper we propose a method for the design of feedforward neural classifiers based on regularization and adaptive architectures. Using a penalized maximum likelihood scheme we derive a modified form of the entropy error measure and an algebraic estimate of the test error. In conjunction with optimal brain damage pruning the test error estimate is used to optimize the network architecture. The scheme is evaluated on an artificial and a real world problem

U2 - 10.1109/NNSP.1996.548352

DO - 10.1109/NNSP.1996.548352

M3 - Article in proceedings

SN - 07-80-33550-3

SP - 223

EP - 232

BT - Proceedings of the IEEE Signal Processing Society Workshop Neural Networks for Signal Processing

PB - IEEE

T2 - Neural Network for Signal Processing

Y2 - 1 January 1996

ER -

Design and evaluation of neural classifiers

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this