GENERALIZATION AND EXCLUSIVE ALLOCATION OF CREDIT IN UNSUPERVISED CATEGORY LEARNING

Citation
Ja. Marshall et Vs. Gupta, GENERALIZATION AND EXCLUSIVE ALLOCATION OF CREDIT IN UNSUPERVISED CATEGORY LEARNING, Network, 9(2), 1998, pp. 279-302
Citations number
31
Categorie Soggetti
Computer Science Artificial Intelligence",Neurosciences,"Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence
Journal title
ISSN journal
0954898X
Volume
9
Issue
2
Year of publication
1998
Pages
279 - 302
Database
ISI
SICI code
0954-898X(1998)9:2<279:GAEAOC>2.0.ZU;2-R
Abstract
A new way of measuring generalization in unsupervised learning is pres ented. The measure is based on an exclusive allocation, or credit assi gnment, criterion. In a classifier that satisfies the criterion, input patterns are parsed so that the credit for each input feature is assi gned exclusively to one of multiple, possibly overlapping, output cate gories. Such a classifier achieves context-sensitive, global represent ations of pattern data. Two additional constraints, sequence masking a nd uncertainty multiplexing, are described; these can be used to refin e the measure of generalization. The generalization performance of EXI N networks, winner-take-all competitive learning networks, linear deco rrelator networks, and Nigrin's SONNET-2 network are compared.