Asymptotitically [sic] stable recurrent neural networks : theory and application

Simple item page
dc.contributor.authorDorocicz, John Tadeuszen_US
dc.date.accessioned2024-08-13T20:18:35Z
dc.date.available2024-08-13T20:18:35Z
dc.date.copyright1997en_US
dc.date.issued1997
dc.degree.departmentDepartment of Electrical and Computer Engineering
dc.degree.levelMaster of Applied Science M.A.Sc.en
dc.description.abstractThis thesis will outline the basis for some types of artificial neural networks. In particular a special type of recurrent neural network that has been proven to be asymptotically stable will be studied. The theory required to train such a neural network will be presented. A number of heuristics designed to improve the training of the asymptotically stable recurĀ­rent neural network and the results of these heuristics on a variety of data sets will be preĀ­sented. An application for the asymptotically stable recurrent neural network involving the monitoring of cable television trunk amplifiers will also be described.
dc.format.extent134 pages
dc.identifier.urihttps://hdl.handle.net/1828/17637
dc.rightsAvailable to the World Wide Weben_US
dc.titleAsymptotitically [sic] stable recurrent neural networks : theory and applicationen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
DOROCICZ_John_Tadeusz_MSc_1997_708072.pdf
Size:
2.11 MB
Format:
Adobe Portable Document Format
Download

Collections

Electronic Theses and Dissertations (ETD)
 
University of Victoria Libraries

We acknowledge and respect the LəkĢ“Ź·É™Å‹É™n (Songhees and Esquimalt) Peoples on whose territory the university stands, and the LəkĢ“Ź·É™Å‹É™n and WĢ±SƁNEĆ Peoples whose historical relationships with the land continue to this day.