Context dependent learning in neural networks

L.J. Spreeuwers; B.J. Van Der Zwaag; F. Van Der Heijden

doi:10.1049/cp:19950736

Context dependent learning in neural networks

L.J. Spreeuwers, B.J. Van Der Zwaag, F. Van Der Heijden

University of Twente

Research output: Chapter in Book/Report/Conference proceeding › Contribution to conference proceeding › Academic › peer-review

Abstract

In this paper an extension to the standard error back-propagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent information is important, a major improvement in performance is obtained.

Original language	English
Title of host publication	Fifth International Conference on Image Processing and its Applications, 1995.
Publisher	IET
Pages	632-636
Number of pages	5
ISBN (Print)	0-85296-642-3
DOIs	https://doi.org/10.1049/cp:19950736
Publication status	Published - 6 Jul 1995
Externally published	Yes
Event	Fifth International Conference on Image Processing and its Applications, 1995. - Edinburgh Duration: 4 Jul 1995 → 6 Jul 1995

Conference

Conference	Fifth International Conference on Image Processing and its Applications, 1995.
Period	4/07/95 → 6/07/95

Keywords

backpropagation
feedforward neural networks
multilayer perceptrons

Access to Document

10.1049/cp:19950736

Cite this

@inproceedings{b38d3c2b49bf43ff95855b11a276a5a6,

title = "Context dependent learning in neural networks",

abstract = "In this paper an extension to the standard error back-propagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent information is important, a major improvement in performance is obtained.",

keywords = "backpropagation, feedforward neural networks, multilayer perceptrons, terugpropagatie, feedforward neuraal netwerk, meerlaagse perceptronen",

author = "L.J. Spreeuwers and Zwaag, {B.J. Van Der} and Heijden, {F. Van Der}",

year = "1995",

month = jul,

day = "6",

doi = "10.1049/cp:19950736",

language = "English",

isbn = "0-85296-642-3",

pages = "632--636",

booktitle = "Fifth International Conference on Image Processing and its Applications, 1995.",

publisher = "IET",

note = "Fifth International Conference on Image Processing and its Applications, 1995. ; Conference date: 04-07-1995 Through 06-07-1995",

}

TY - GEN

T1 - Context dependent learning in neural networks

AU - Spreeuwers, L.J.

AU - Zwaag, B.J. Van Der

AU - Heijden, F. Van Der

PY - 1995/7/6

Y1 - 1995/7/6

N2 - In this paper an extension to the standard error back-propagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent information is important, a major improvement in performance is obtained.

AB - In this paper an extension to the standard error back-propagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent information is important, a major improvement in performance is obtained.

KW - backpropagation

KW - feedforward neural networks

KW - multilayer perceptrons

KW - terugpropagatie

KW - feedforward neuraal netwerk

KW - meerlaagse perceptronen

UR - https://ieeexplore.ieee.org/document/465472/

U2 - 10.1049/cp:19950736

DO - 10.1049/cp:19950736

M3 - Contribution to conference proceeding

SN - 0-85296-642-3

SP - 632

EP - 636

BT - Fifth International Conference on Image Processing and its Applications, 1995.

PB - IET

T2 - Fifth International Conference on Image Processing and its Applications, 1995.

Y2 - 4 July 1995 through 6 July 1995

ER -

Context dependent learning in neural networks

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this