Skip to main navigation Skip to search Skip to main content

Prediction Error of a Fault Tolerant Neural Network

John Sum, Chi-Sing Leung, Kevin Ho

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

For more than a decade, prediction error has been one powerful tool to measure the performance of a neural network. In this paper, we extend the technique to a kind of fault tolerant neural network. Consider a neural network to be suffering from multiple-node fault, a formulae similar to that of Generalized Prediction Error has been derived. Hence, the effective number of parameter of such a fault tolerant neural network is obtained. A difficulty in obtaining the mean prediction error is discussed and then a simple procedure for estimation of the prediction error empirically is suggested.
Original languageEnglish
Title of host publicationNeural Information Processing
Subtitle of host publication13th International Conference, ICONIP 2006, Proceedings
EditorsIrwin King, Jun Wang, Laiwan Chan, DeLiang Wang
PublisherSpringer Verlag
Pages521-528
ISBN (Print)3540464794, 9783540464792
DOIs
Publication statusPublished - Oct 2006
Event13th International Conference on Neural Information Processing (ICONIP 2006) - Hong Kong, China
Duration: 3 Oct 20066 Oct 2006

Publication series

NameLecture Notes in Computer Science
Volume4232
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference13th International Conference on Neural Information Processing (ICONIP 2006)
PlaceChina
CityHong Kong
Period3/10/066/10/06

Fingerprint

Dive into the research topics of 'Prediction Error of a Fault Tolerant Neural Network'. Together they form a unique fingerprint.

Cite this