Hill-Climbing Theories of Learning
Interim rept. Jul 1986-Jul 1987
CALIFORNIA UNIV IRVINE SCHOOL OF INFORMATION AND COMPUTER SCIENCE
Pagination or Media Count:
Much human learning appears to be gradual and unconscious, suggesting a very limited form of search through the space of hypotheses. We propose hill climbing as a framework for such learning and consider a number of systems that learn in this manner. We focus on CLASSIT, a model of concept formation that incrementally acquires a conceptual hierarchy, and MAGGIE, a model of skill improvement that alters motor schemas in response to errors. Both models integrate the processes of learning and performance. Keywords Artificial intelligence Data processing Computer models Computer applications.