creators_name: Spratling, Michael creators_name: Hayes, Gillian type: journalp datestamp: 2000-11-15 lastmod: 2011-03-11 08:54:27 metadata_visibility: show title: Learning synaptic clusters for non-linear dendritic processing ispublished: pub subjects: comp-sci-neural-nets subjects: neuro-mod full_text_status: public abstract: Nonlinear dendritic processing appears to be a feature of biological neurons and would also be of use in many applications of artificial neural networks. This paper presents a model of an initially standard linear unit which uses unsupervised learning to find clusters of inputs within which inactivity at one synapse can occlude the activity at the other synapses. date: 2000 date_type: published publication: Neural Processing Letters volume: 11 number: 1 pagerange: 17-27 refereed: TRUE citation: Spratling, Michael and Hayes, Gillian (2000) Learning synaptic clusters for non-linear dendritic processing. [Journal (Paginated)] document_url: http://cogprints.org/1109/2/sigma_pi.ps