An unsupervised dual-network connectionist model of rule emergence in category learning. Export

@article{Cowell:2007, abstract = {We develop an unsupervised dual-network” connectionist model of category learning in which rules gradually emerge from a standard Kohonen network. The architecture is based on the interaction of a statistical-learning (Kohonen) network and a competitive-learning rule network. The rules that emerge in the rule network are weightings of individual features according to their importance for categorisation. Once the combined system has learned a particular rule, it de-emphasizes those features that are not sufficient for categorisation, thus allowing correct classification of novel, but atypical, stimuli, for which a standard Kohonen network fails. We explain the principles and architectural details of the model and show how it works correctly for stimuli that are misclassified by a standard Kohonen network.}, author = {Cowell, Rosemary A. and French, Robert M.}, booktitle = {Proceedings of the Second European Cognitive Science Conference, 2007.}, citeulike-article-id = {4774842}, citeulike-linkout-0 = {http://leadserv.u-bourgogne.fr/~rosie/papers/Cowell_French_EuroCogSci2007.pdf}, keywords = {categorisation, neural-networks, phd, rule-extraction, rules}, posted-at = {2009-06-08 10:10:42}, priority = {0}, title = {An unsupervised dual-network connectionist model of rule emergence in category learning.}, url = {http://leadserv.u-bourgogne.fr/~rosie/papers/Cowell_French_EuroCogSci2007.pdf}, year = {2007} }

TY - JOUR ID - Cowell:2007 L3 - citeulike-article-id:4774842 N2 - We develop an unsupervised dual-network” connectionist model of category learning in which rules gradually emerge from a standard Kohonen network. The architecture is based on the interaction of a statistical-learning (Kohonen) network and a competitive-learning rule network. The rules that emerge in the rule network are weightings of individual features according to their importance for categorisation. Once the combined system has learned a particular rule, it de-emphasizes those features that are not sufficient for categorisation, thus allowing correct classification of novel, but atypical, stimuli, for which a standard Kohonen network fails. We explain the principles and architectural details of the model and show how it works correctly for stimuli that are misclassified by a standard Kohonen network. TI - An unsupervised dual-network connectionist model of rule emergence in category learning. T2 - Proceedings of the Second European Cognitive Science Conference, 2007. KW - categorisation KW - neural-networks KW - phd KW - rule-extraction KW - rules AU - Cowell, Rosemary AU - French, Robert PY - 2007/// UR - http://leadserv.u-bourgogne.fr/~rosie/papers/Cowell_French_EuroCogSci2007.pdf ER -