hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Training neural networks by stochastic optimisation
Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).ORCID iD: 0000-0003-2185-8973
Department of Applied Electronics, Kaunas University of Technology, Lithuania.
2000 (English)In: Neurocomputing, ISSN 0925-2312, E-ISSN 1872-8286, Vol. 30, no 1-4, p. 153-172Article in journal (Refereed) Published
Abstract [en]

We present a stochastic learning algorithm for neural networks. The algorithm does not make any assumptions about transfer functions of individual neurons and does not depend on a functional form of a performance measure. The algorithm uses a random step of varying size to adapt weights. The average size of the step decreases during learning. The large steps enable the algorithm to jump over local maxima/minima, while the small ones ensure convergence in a local area. We investigate convergence properties of the proposed algorithm as well as test the algorithm on four supervised and unsupervised learning problems. We have found a superiority of this algorithm compared to several known algorithms when testing them on generated as well as real data.

Place, publisher, year, edition, pages
Amsterdam: Elsevier , 2000. Vol. 30, no 1-4, p. 153-172
Keywords [en]
Neural networks, Benchmarking, Convergence of numerical methods, Learning algorithms, Problem solving, Random processes, Simulated annealing, Transfer functions, Stochastic optimisation
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:hh:diva-3534DOI: 10.1016/S0925-2312(99)00123-XISI: 000084063300017Scopus ID: 2-s2.0-0033991233OAI: oai:DiVA.org:hh-3534DiVA, id: diva2:286845
Available from: 2010-01-15 Created: 2009-12-01 Last updated: 2018-01-12Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records BETA

Verikas, Antanas

Search in DiVA

By author/editor
Verikas, Antanas
By organisation
Halmstad Embedded and Intelligent Systems Research (EIS)
In the same journal
Neurocomputing
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 135 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf