Change search
ReferencesLink to record
Permanent link

Direct link
Exploring Learning in Evolutionary Artificial Neural Networks
Norwegian University of Science and Technology, Faculty of Information Technology, Mathematics and Electrical Engineering, Department of Computer and Information Science.
2011 (English)MasteroppgaveStudent thesis
Abstract [en]

Evolutionary artificial neural networks can adapt to new circumstances, and handle slight changes without catastrophic failure. However, under constantly changing circumstances, resulting in unpredictable grounds for evaluating success, the lack of memory of previous adaptations are a limiting factor. While further evolution can allow adaptations to new changes, the same is required for a return to a previous environment. To reduce the need for further evolution to deal with previously seen problems, this thesis looks at an approach to encourage previous knowledge to be retained across generations. It does this using back propagation in conjunction with an implementation of the HyperNEAT neuroevolutionary algorithm.

Place, publisher, year, edition, pages
Institutt for datateknikk og informasjonsvitenskap , 2011. , 67 p.
Keyword [no]
ntnudaim:6526, MTDT datateknikk, Intelligente systemer
URN: urn:nbn:no:ntnu:diva-15689Local ID: ntnudaim:6526OAI: diva2:505170
Available from: 2012-02-23 Created: 2012-02-23

Open Access in DiVA

fulltext(1544 kB)212 downloads
File information
File name FULLTEXT01.pdfFile size 1544 kBChecksum SHA-512
Type fulltextMimetype application/pdf
cover(152 kB)34 downloads
File information
File name COVER01.pdfFile size 152 kBChecksum SHA-512
Type coverMimetype application/pdf

By organisation
Department of Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 212 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: 31 hits
ReferencesLink to record
Permanent link

Direct link