creators_name: Spratling, Michael creators_name: Hayes, Gillian type: confpaper datestamp: 2000-11-15 lastmod: 2011-03-11 08:54:26 metadata_visibility: show title: Learning sensory-motor cortical mappings without training ispublished: pub subjects: comp-sci-neural-nets subjects: comp-sci-robot subjects: neuro-mod full_text_status: public keywords: sensorimotor control, neural networks abstract: This paper shows how the relationship between two arrays of artificial neurons, representing different cortical regions, can be learned. The algorithm enables each neural network to self-organise into a topological map of the domain it represents at the same time as the relationship between these maps is found. Unlike previous methods learning is achieved without a separate training phase; the algorithm which learns the mapping is also that which performs the mapping. date: 1998 date_type: published pagerange: 339-344 refereed: TRUE citation: Spratling, Michael and Hayes, Gillian (1998) Learning sensory-motor cortical mappings without training. [Conference Paper] document_url: http://cogprints.org/1106/2/cort_map.ps