A neural network model of concept-influenced segmentation

Goldstone, R. L. (2000). A neural network model  of concept-influenced segmentation. Proceedings of the Twenty-second Annual Conference of the Cognitive Science Society.  Hillsdale, New Jersey: Lawrence Erlbaum Associates. (pp. 172-177).

Several models of categorization assume that fixed perceptual representations are combined together to determine categorizations.  This research explores the possibility that categorization experience alters, rather than simply uses, descriptions of objects.  Based on results from human experiments, a  model is presented in which a competitive learning network is first given categorization training, and then is given a subsequent segmentation task, using the same network weights.  Category learning establishes detectors for stimulus parts that are diagnostic, and these detectors, once established, bias the interpretation of subsequent objects to be segmented.

Download PDF version of this paper