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
The Effects of Using Results from Inversion by Evolutionary Algorithms to Retrain Artificial Neural Networks
Högskolan i Skövde, Institutionen för datavetenskap.
2000 (engelsk)Independent thesis Basic level (degree of Bachelor)Oppgave
Abstract [en]

The aim of inverting artificial neural networks (ANNs) is to find input patterns that are strongly classified as a predefined class. In this project an ANN is inverted by an evolutionary algorithm. The network is retrained by using the patterns extracted by the inversion as counter-examples, i.e. to classify the patterns as belonging to no class, which is the opposite of what the network previously did. The hypothesis is that the counter-examples extracted by the inversion will cause larger updates of the weights of the ANN and create a better mapping than what is caused by retraining using randomly generated counter-examples. This hypothesis is tested on recognition of pictures of handwritten digits. The tests indicate that this hypothesis is correct. However, the test- and training errors are higher when retraining using counter-examples, than for training only on examples of clean digits. It can be concluded that the counter-examples generated by the inversion have a great impact on the network. It is still unclear whether the quality of the network can be improved using this method.

sted, utgiver, år, opplag, sider
Skövde: Institutionen för datavetenskap , 2000. , s. 35
Emneord [en]
Artificial neural networks, inversion, evolutionary algorithms
HSV kategori
Identifikatorer
URN: urn:nbn:se:his:diva-411OAI: oai:DiVA.org:his-411DiVA, id: diva2:2783
Presentation
(engelsk)
Uppsök
Technology
Veileder
Tilgjengelig fra: 2007-12-19 Laget: 2007-12-19 Sist oppdatert: 2018-01-12

Open Access i DiVA

fulltekst(2246 kB)145 nedlastinger
Filinformasjon
Fil FULLTEXT01.psFilstørrelse 2246 kBChecksum MD5
691f71610a1ac373d737ea7b49a427bbd2776d5f7954842943744f5d8a05c3a26904ea4c
Type fulltextMimetype application/postscript
fulltekst(350 kB)98 nedlastinger
Filinformasjon
Fil FULLTEXT02.pdfFilstørrelse 350 kBChecksum SHA-512
ddf8c3e8f0e5646e0967e3356574647d546c746a9b2c1d8bd088910f2eaad26503406a98c78c0d706c565d0b985c0462d402d1e3c4b1fa41eac15e9c90c89ff0
Type fulltextMimetype application/pdf

Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 243 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: 255 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