Detailed learning in narrow fields: towards a neural network model of autism
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)
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
IdentifiersURN: urn:nbn:se:ltu:diva-20117DOI: 10.1007/3-540-44989-2_99Local ID: 212cc980-5f4f-11db-8cbe-000ea68e967bISBN: 978-3-540-40408-8OAI: oai:DiVA.org:ltu-20117DiVA: diva2:993161
Validerad; 2003; 20060922 (ysko)2016-09-292016-09-29Bibliographically approved