title: Neural model of transfer-of-binding in visual relative motion perception. creator: Marshall, J.A. creator: Schmitt, C.P. creator: Kalarickal, G.J. creator: Alley, R.K. subject: Cognitive Psychology subject: Artificial Intelligence subject: Complexity Theory subject: Machine Learning subject: Machine Vision subject: Neural Nets subject: Statistical Models subject: Perceptual Cognitive Psychology description: 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 type: Preprint type: PeerReviewed format: application/postscript identifier: http://cogprints.org/436/2/xfer-bind9701.ps identifier: 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] relation: http://cogprints.org/436/