Multimodal feedforward self-organizing maps
2005 (English)In: Computational intelligence and security: international conference, CIS 2005, Xi´an, China, December 15-19, 2005; proceedings / [ed] Yue Hao, Berlin: Encyclopedia of Global Archaeology/Springer Verlag, 2005, 81-88 p.Conference paper (Refereed)
We introduce a novel system of interconnected Self- Organizing Maps that can be used to build feedforward and recurrent networks of maps. Prime application of interconnected maps is in modelling systems that operate with multimodal data as for example in visual and auditory cortices and multimodal association areas in cortex. A detailed example of animal categorization in which the feedworward network of self-organizing maps is employed is presented. In the example we operate with 18-dimensional data projected up on the 19-dimensional hyper-sphere so that the “dot-product” learning law can be used. One potential benefit of the multimodal map is that it allows a rich structure of parallel unimodal processing with many maps involved, followed by convergence into multimodal maps. More complex stimuli can therefore be processed without a growing map size.
Place, publisher, year, edition, pages
Berlin: Encyclopedia of Global Archaeology/Springer Verlag, 2005. 81-88 p.
Lecture Notes in Computer Science, ISSN 0302-9743 ; 3801
Research subject Industrial Electronics
IdentifiersURN: urn:nbn:se:ltu:diva-27638DOI: 10.1007/11596448_11Local ID: 12631930-3814-11df-be5c-000ea68e967bISBN: 978-3-540-30818-8OAI: oai:DiVA.org:ltu-27638DiVA: diva2:1000826
International Conference on Computational Intelligence and Security : 15/12/2005 - 19/12/2005
Validerad; 2005; 20100325 (andbra)2016-09-302016-09-30Bibliographically approved