Bringing knowing-when and knowing-what together: Periodically tuned categorization and category-based timing modeled with the Recurrent Oscillatory Self-organizing Map (ROSOM)
2000 (English)In: Minds and Machines, ISSN 0924-6495, E-ISSN 1572-8641, Vol. 10, no 2, 203-229 p.Article in journal (Refereed) Published
The study addresses the cyclically temporal aspect of sequence recognition, storage and recall using the Recurrent Oscillatory Self-Organizing Map (ROSOM), first introduced by Kaipainen, Papadopoulos and Karhu (1997). The unique solution of the network is that oscillatory States are assigned to network units, corresponding to their `readiness-to-fire'. The ROSOM is a categorizer, a temporal sequence storage system and a periodicity detector designed for use in an ambiguous cyclically repetitive environment. As its external input, the model accepts a multidimensional stream of environment-describing feature configurations with implicit periodicities. The output of the model is one or a few closed cycles abstracted from such a stream, mapped as trajectories on a two-dimensional sheet with an organization reminiscent of multi-dimensional scaling. The model's capabilities are explored with a variety of workbench data.
Place, publisher, year, edition, pages
2000. Vol. 10, no 2, 203-229 p.
Media and Communication Technology
IdentifiersURN: urn:nbn:se:sh:diva-12235DOI: 10.1023/A:1008317204895ISI: 000088591400002OAI: oai:DiVA.org:sh-12235DiVA: diva2:448591