Research on Concept and Schema Learning


An agent can truly understand the meaning of its knowledge structures, and utilize them most effectively, only if that knowledge is grounded on sensorimotor interactions with the world. We aim at building systems that learn such grounded representations, from basic causal concepts to high-level schemas of visual scenes. Our projects in this area are described below; for more details, see publications on Concept and Schema Learning. Related topics are described in the Natural Language Processing, Visual Cortex, and Self-Organization pages.


Back to Research Projects
Back to UTCS Neural Networks home page
risto@cs.utexas.edu
Last update: 1.6 2001/11/18 03:07:13 risto