SUSTAIN: A Network Model of Category Learning.
- 1 January 2004
- journal article
- Published by American Psychological Association (APA) in Psychological Review
- Vol. 111 (2), 309-332
- https://doi.org/10.1037/0033-295x.111.2.309
Abstract
SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUS- TAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clus- ters are available to explain future events and can themselves evolve into prototypes/attractors/rules. Importantly, SUSTAIN's discovery of category substructure is aected not only by the structure of the world, but by the nature of the learning task and the learner's goals. SUSTAIN successfully ex- tends category learning models to studies of inference learning, unsupervised learning, category construction, and contexts where identification learning is faster than classification learning.Keywords
This publication has 81 references indexed in Scilit:
- Three deadly sins of category learning modelersBehavioral and Brain Sciences, 2001
- Equivalent inferences using transformationsCommunications in Statistics - Theory and Methods, 1996
- Comparing decision bound and exemplar models of categorizationPerception & Psychophysics, 1993
- Human Category Learning: Implications for Backpropagation ModelsConnection Science, 1993
- Is an Object an Object an Object? Cognitive and Neuropsychological Investigations of Domain Specificity in Visual Object RecognitionCurrent Directions in Psychological Science, 1992
- Benefits of gain: speeded learning and minimal hidden layers in back-propagation networksIEEE Transactions on Systems, Man, and Cybernetics, 1991
- Dynamic Node Creation in Backpropagation NetworksConnection Science, 1989
- A massively parallel architecture for a self-organizing neural pattern recognition machineComputer Vision, Graphics, and Image Processing, 1987
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982
- General Principles of Classification and Nomenclature in Folk BiologyAmerican Anthropologist, 1973