Change search
ReferencesLink to record
Permanent link

Direct link
Detailed learning in narrow fields: towards a neural network model of autism
LuleƄ University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.
2003 (English)In: Artifcial Neural Networks and Neural Information Processing: Joint International Conference ICANN/ICONIP 2003 Istanbul, Turkey, June 26-29, 2003 Proceedings, Berlin: Encyclopedia of Global Archaeology/Springer Verlag, 2003, 830-838 p.Chapter in book (Other academic)
Abstract [en]

Autism is a developmental disorder in which attention shifting is known to be restricted. Using an artificial neural network model of learning we show how detailed learning in narrow fields develops when attention shifting between different sources of stimuli is restricted by familiarity preference. Our model is based on modified Self-Organizing Maps (SOM) supported by the attention shift mechanism. The novelty seeking and the attention shifting restricted by familiarity preference learning modes are investigated for stimuli of low and high dimensionality which requires different techniques to visualise feature maps. To make learning more biologically plausible we project the stimuli onto a unity hyper-sphere. The distance between a stimulus and a weight vector can now be simply measured by the post-synaptic activities. The modified "dot-product" learning law that keeps evolving weights on the surface of the hyper-sphere has been employed.

Place, publisher, year, edition, pages
Berlin: Encyclopedia of Global Archaeology/Springer Verlag, 2003. 830-838 p.
Lecture Notes in Computer Science, ISSN 0302-9743 ; 2714
Research subject
Industrial Electronics
URN: urn:nbn:se:ltu:diva-20117DOI: 10.1007/3-540-44989-2_99Local ID: 212cc980-5f4f-11db-8cbe-000ea68e967bISBN: 978-3-540-40408-8OAI: diva2:993161
Validerad; 2003; 20060922 (ysko)Available from: 2016-09-29 Created: 2016-09-29Bibliographically approved

Open Access in DiVA

fulltext(225 kB)0 downloads
File information
File name FULLTEXT01.pdfFile size 225 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Paplinski, AndrewGustafsson, Lennart
By organisation
Embedded Internet Systems Lab

Search outside of DiVA

GoogleGoogle Scholar
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

Altmetric score

ReferencesLink to record
Permanent link

Direct link