creators_name: Marshall, J.A.
creators_name: Schmitt, C.P.
creators_name: Kalarickal, G.J.
creators_name: Alley, R.K.
type: preprint
datestamp: 1998-04-28
lastmod: 2011-03-11 08:53:55
metadata_visibility: show
title: Neural model of transfer-of-binding in visual relative motion perception.
subjects: cog-psy
subjects: comp-sci-art-intel
subjects: comp-sci-complex-theory
subjects: comp-sci-mach-learn
subjects: comp-sci-mach-vis
subjects: comp-sci-neural-nets
subjects: comp-sci-stat-model
subjects: percep-cog-psy
full_text_status: public
abstract: A new way of measuring generalization in unsupervised learning is presented. The measure is based on an exclusive allocation, or credit assignment, criterion. In a classifier that satisfies the criterion, input patterns are parsed so that the credit for each input feature is assigned exclusively to one of multiple, possibly overlapping, output categories. Such a classifier achieves context-sensitive, global representations of pattern data. Two additional constraints, sequence masking and uncertainty multiplexing, are described; these can be used to refine the measure of generalization. The generalization performance of EXIN networks, winner-take-all competitive learning networks, linear decorrelator networks, and Nigrin's SONNET-2 network is compared.
date: 1998-01
date_type: published
refereed: TRUE
citation:   Marshall, J.A. and Schmitt, C.P. and Kalarickal, G.J. and Alley, R.K.  (1998) Neural model of transfer-of-binding in visual relative motion perception.  [Preprint]     
document_url: http://cogprints.org/436/2/xfer-bind9701.ps