Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

Local Minima and Attractors at Infinity in Gradient Descent Learning Algorithms

Simple item page
dc.contributor.authorBlackmore, Kim
dc.contributor.authorWilliamson, Robert
dc.contributor.authorMareels, Iven
dc.date.accessioned2022-08-12T01:19:38Z
dc.date.issued1996
dc.date.updated2021-08-01T08:31:58Z
dc.description.abstractIn the paper 'Learning Nonlinearly Parametrized Decision Regions", an online scheme for learning a very general class of decision regions is given, together with conditions on both the parametrization and on the sequence of input examples under which good learning can be guaranteed to occur. In this paper, we discuss these conditions, in particular the requirement that there be no non-global local minima of the relevant error function, and the more speci c problem of no attractor at in nity. Somewhat simpler su cient conditions are given. A number of examples are discussed.en_AU
dc.format.mimetypeapplication/pdfen_AU
dc.identifier.issn1052-0600en_AU
dc.identifier.urihttp://hdl.handle.net/1885/270414
dc.language.isoen_AUen_AU
dc.publisherBirkhauser Verlagen_AU
dc.rights© 1996 The authorsen_AU
dc.sourceJournal of Mathematical Systems, Estimation, and Controlen_AU
dc.subjecterror functionen_AU
dc.subjectlocal minimumen_AU
dc.subjectattractor at in finityen_AU
dc.subjectlearningen_AU
dc.subjectdecision regionen_AU
dc.titleLocal Minima and Attractors at Infinity in Gradient Descent Learning Algorithmsen_AU
dc.typeJournal articleen_AU
local.bibliographicCitation.issue2en_AU
local.bibliographicCitation.lastpage18en_AU
local.bibliographicCitation.startpage1en_AU
local.contributor.affiliationBlackmore, Kim, College of Engineering and Computer Science, ANUen_AU
local.contributor.affiliationWilliamson, Robert, College of Engineering and Computer Science, ANUen_AU
local.contributor.affiliationMareels, Iven M, College of Engineering and Computer Science, ANUen_AU
local.contributor.authoruidBlackmore, Kim, u4036671en_AU
local.contributor.authoruidWilliamson, Robert, u9000163en_AU
local.contributor.authoruidMareels, Iven M, u4023949en_AU
local.description.embargo2099-12-31
local.description.notesImported from ARIESen_AU
local.identifier.absfor461199 - Machine learning not elsewhere classifieden_AU
local.identifier.ariespublicationu4153526xPUB22en_AU
local.identifier.citationvolume6en_AU
local.type.statusPublished Versionen_AU

Downloads

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Local Minima.pdf
Size:
289.49 KB
Format:
Adobe Portable Document Format
Description:
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2026 LYRASIS