Implementation of the backpropagation algorithm on iPSC/2 hypercube multicomputer system

buir.advisorOflazer, Kemal
dc.contributor.authorErcoşkun, Deniz
dc.date.accessioned2016-01-08T20:08:42Z
dc.date.available2016-01-08T20:08:42Z
dc.date.issued1990
dc.descriptionAnkara : The Department of Computer Engineering and Information Science and the Institute of Engineering and Sciences of Bilkent Univ., 1990.en_US
dc.descriptionThesis (Master's) -- Bilkent University, 1990.en_US
dc.descriptionIncludes bibliographical references.en_US
dc.description.abstractBackpropagation is a supervised learning procedure for a class of artificial neural networks. It has recently been widely used in training such neural networks to perform relatively nontrivial tasks like text-to-speech conversion or autonomous land vehicle control. However, the slow rate of convergence of the basic backpropagation algorithm has limited its application to rather small networks since the computational requirements grow significantly as the network size grows. This thesis work presents a parallel implementation of the backpropagation learning algorithm on a hypercube multicomputer system. The main motivation for this implementation is the construction of a parallel training and simulation utility for such networks, so that larger neural network applications can be experimented with.en_US
dc.description.provenanceMade available in DSpace on 2016-01-08T20:08:42Z (GMT). No. of bitstreams: 1 1.pdf: 78510 bytes, checksum: d85492f20c2362aa2bcf4aad49380397 (MD5)en
dc.description.statementofresponsibilityErcoşkun, Denizen_US
dc.format.extentxi, 72 leavesen_US
dc.identifier.urihttp://hdl.handle.net/11693/17264
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subject.lccQA76.58 .E73 1990en_US
dc.subject.lcshParallel processing (Electronic computers).en_US
dc.subject.lcshNeural networks (Computer science).en_US
dc.subject.lcshBack propagation (Artificial intelligence).en_US
dc.subject.lcshIntegrated circuits--Very large scale integration--Design and construction.en_US
dc.subject.lcshAlgorithms.en_US
dc.subject.lcshHypercube networks (Computer networks).en_US
dc.titleImplementation of the backpropagation algorithm on iPSC/2 hypercube multicomputer systemen_US
dc.typeThesisen_US
thesis.degree.disciplineComputer Engineering
thesis.degree.grantorBilkent University
thesis.degree.levelMaster's
thesis.degree.nameMS (Master of Science)

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
B007637.pdf
Size:
2.06 MB
Format:
Adobe Portable Document Format
Description:
Full printable version