Training, dynamics, and complexity of architecture-specific recurrent neural networks

Simple item page
dc.contributor.advisorCloete, I.en_ZA
dc.contributor.authorLudik, Jacquesen_ZA
dc.contributor.otherStellenbosch University. Faculty of Science. Dept. of Computer Science.
dc.date.accessioned2012-08-27T11:39:03Z
dc.date.available2012-08-27T11:39:03Z
dc.date.issued1994
dc.descriptionDissertation (Ph. D.) -- University of Stellenbosch, 1994.
dc.description.abstractENGLISH ABSTRACT: This dissertation describes the main results of a pioneering effort to develop novel architectures, training strategies, dynamics analysis techniques and theoretical complexity results for architecure-specific reccurent neural network (ASRNNs). To put the study of ASRNNs into an appropriate perspective, a temporal processing framework that describes the different neural network approaches taken, was constructed. ASRNNs are more powerful than non-recurrent networks and computationally less expensive, more stable, and easier to study than general-purpose recurrent networks. The focus was on Elman, Jordan, and Temporal Autoassociation ASRNNs using discrete-time backpropagation.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMIG: Hierdie proefskrif beskryf die belangrikste resultate van baanbrekerswerk om nuwe argitekture, afrigstratigee, dinamiese analise tegniek en teoretiese kompleksiteitsresultate vir argitektuur-spesifieke terugvoer neurale netwerke (ASTNNe) te ontwikkel. Om die studie van ASTNNe in 'n gepaste perspektief te plaas, is 'n temporaleverwerkingsraamwerk daargestel wat die verskillende neurale netwerk benaderings wat ingespan word, beskryf. ASTNNe is kragtiger as nie-terugvoer netwerke en minder berekeningsintensief, meer stabiel, en eenvoudiger om te bestudeer as meerdoelige terugvoer netwerke. In hierdie studie word spesifiek gefokus op Elman, Jordan, en Temporale Outoassosiasie ASTNNe wat van die terugpropagering leer-algoritme gebruik maak.af_ZA
dc.format.extent244 pages : illustrations.
dc.identifier.urihttp://hdl.handle.net/10019.1/58622
dc.language.isoen_ZA
dc.publisherStellenbosch : Stellenbosch University
dc.rights.holderStellenbosch University
dc.subjectNeural networks (Computer science)en_ZA
dc.subjectComputer architectureen_ZA
dc.subjectSystem analysisen_ZA
dc.subjectDissertations -- Computer scienceen_ZA
dc.subjectUCTDen_ZA
dc.titleTraining, dynamics, and complexity of architecture-specific recurrent neural networksen_ZA
dc.typeThesis
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ludik_training_1994.pdf
Size:
25.85 MB
Format:
Adobe Portable Document Format
Description:
Download thesis
Download
Collections
Doctoral Degrees (Computer Science)