his.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Comparison of two methods for evolving recurrent artificial neural networks for
Högskolan i Skövde.
1998 (svensk)Independent thesis Basic level (degree of Bachelor)Oppgave
Abstract [sv]

n this dissertation a comparison of two evolutionary methods for evolving ANNs for robot control is made. The methods compared are SANE with enforced sub-population and delta-coding, and marker-based encoding. In an attempt to speed up evolution, marker-based encoding is extended with delta-coding. The task selected for comparison is the hunter-prey task. This task requires the robot controller to posess some form of memory as the prey can move out of sensor range. Incremental evolution is used to evolve the complex behaviour that is required to successfully handle this task. The comparison is based on computational power needed for evolution, and complexity, robustness, and generalisation of the resulting ANNs. The results show that marker-based encoding is the most efficient method tested and does not need delta-coding to increase the speed of evolution process. Additionally the results indicate that delta-coding does not increase the speed of evolution with marker-based encoding.

sted, utgiver, år, opplag, sider
1998. , s. 54
Emneord [sv]
recurrent artificial neural networks, genetic algorithms, robot controllers, evo
HSV kategori
Identifikatorer
URN: urn:nbn:se:his:diva-155OAI: oai:DiVA.org:his-155DiVA, id: diva2:2503
Presentation
(engelsk)
Uppsök
Social and Behavioural Science, Law
Veileder
Tilgjengelig fra: 2007-10-12 Laget: 2007-10-12 Sist oppdatert: 2018-01-13

Open Access i DiVA

fulltekst(1247 kB)128 nedlastinger
Filinformasjon
Fil FULLTEXT01.psFilstørrelse 1247 kBChecksum SHA-1
0d9ae5ab6a76bbf3447934faba7c9c91a519ad89c2533132ee5c53c56cbfbaf4b17665df
Type fulltextMimetype application/postscript
fulltekst(404 kB)222 nedlastinger
Filinformasjon
Fil FULLTEXT02.pdfFilstørrelse 404 kBChecksum SHA-512
058d3d4c37cdc5a4aeec64feddbaff10cbe5a0e9909abf93fad37084358852611860c589d3405ff06fdb60fb619533cc170ed12efb2f06ec8bfebd1148fdf658
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 350 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 196 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf