Notice: eScholarship will undergo scheduled maintenance from Tuesday, January 21 to Wednesday, January 22. Some functionality may not be available during this time. Learn more at eScholarship Support.
A system is described which learns to compose sequences of operators into episodes for problem solving. The system incrementally learns when and why operators are applied. Episodes are segmented so that they are generalizable and reusable. The idea of augmenting the instance language with higher level concepts is introduced. The technique of perturbation is described for discovering the essential features for a rule with minimal teacher guidance. The approach is applied to the domain of solving simultaneous linear equations.
Main Content
For improved accessibility of PDF content, download the file to your device.
