his.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
A Comparison of Simple Recurrent and Sequential Cascaded Networks for Formal Language Recognition
Högskolan i Skövde, Institutionen för datavetenskap.
1999 (Engelska)Självständigt arbete på avancerad nivå (magisterexamen)Studentuppsats
Abstract [en]

Two classes of recurrent neural network models are compared in this report, simple recurrent networks (SRNs) and sequential cascaded networks (SCNs) which are first- and second-order networks respectively. The comparison is aimed at describing and analysing the behaviour of the networks such that the differences between them become clear. A theoretical analysis, using techniques from dynamic systems theory (DST), shows that the second-order network has more possibilities in terms of dynamical behaviours than the first-order network. It also revealed that the second order network could interpret its context with an input-dependent function in the output nodes. The experiments were based on training with backpropagation (BP) and an evolutionary algorithm (EA) on the AnBn-grammar which requires the ability to count. This analysis revealed some differences between the two training-regimes tested and also between the performance of the two types of networks. The EA was found to be far more reliable than BP in this domain. Another important finding from the experiments was that although the SCN had more possibilities than the SRN in how it could solve the problem, these were not exploited in the domain tested in this project

Ort, förlag, år, upplaga, sidor
Skövde: Institutionen för datavetenskap , 1999. , s. 143
Nyckelord [en]
Recurrent Neural Networks Formal Language
Nationell ämneskategori
Systemvetenskap, informationssystem och informatik
Identifikatorer
URN: urn:nbn:se:his:diva-391OAI: oai:DiVA.org:his-391DiVA, id: diva2:2761
Presentation
(Engelska)
Uppsök
samhälle/juridik
Handledare
Tillgänglig från: 2007-12-12 Skapad: 2007-12-12 Senast uppdaterad: 2018-01-12

Open Access i DiVA

fulltext(5660 kB)184 nedladdningar
Filinformation
Filnamn FULLTEXT01.psFilstorlek 5660 kBChecksumma SHA-1
98723609a2612b8e08a4b06661754bb24dbf2b85377265514db7dd3ea652a62858d04f6f
Typ fulltextMimetyp application/postscript
fulltext(731 kB)85 nedladdningar
Filinformation
Filnamn FULLTEXT02.pdfFilstorlek 731 kBChecksumma SHA-512
2b8f51d44ae035db2be2e0ffc983b4d7bc9fdafca171136c7d770cfdefd464e6f8ec3f69eed4102aa4143046f00e7e41da04445adeca5e54f2f87eacc3a32e4b
Typ fulltextMimetyp application/pdf

Av organisationen
Institutionen för datavetenskap
Systemvetenskap, informationssystem och informatik

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 269 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 252 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf