his.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
Comparison of two methods for evolving recurrent artificial neural networks for
University of Skövde.
1998 (Swedish)Independent thesis Basic level (degree of Bachelor)Student thesis
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.

Place, publisher, year, edition, pages
1998. , 54 p.
Keyword [sv]
recurrent artificial neural networks, genetic algorithms, robot controllers, evo
National Category
Information Science
Identifiers
URN: urn:nbn:se:his:diva-155OAI: oai:DiVA.org:his-155DiVA: diva2:2503
Presentation
(English)
Uppsok
Social and Behavioural Science, Law
Supervisors
Available from: 2007-10-12 Created: 2007-10-12 Last updated: 2009-09-25

Open Access in DiVA

fulltext(1247 kB)112 downloads
File information
File name FULLTEXT01.psFile size 1247 kBChecksum SHA-1
0d9ae5ab6a76bbf3447934faba7c9c91a519ad89c2533132ee5c53c56cbfbaf4b17665df
Type fulltextMimetype application/postscript
fulltext(404 kB)206 downloads
File information
File name FULLTEXT02.pdfFile size 404 kBChecksum SHA-512
058d3d4c37cdc5a4aeec64feddbaff10cbe5a0e9909abf93fad37084358852611860c589d3405ff06fdb60fb619533cc170ed12efb2f06ec8bfebd1148fdf658
Type fulltextMimetype application/pdf

By organisation
University of Skövde
Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 318 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 141 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