Extending Introspective Learning from Self-Models

David Leake, Mark Wilson

This position paper presents open issues for using self-models to guide introspective learning, focusing on five key types of areas to explore: (1) broadening the range of learning focuses and the range of learning tools which may be brought to bear, (2) learning for self-understanding as well as self-repair, (3) making model-based approaches more sensitive to processing characteristics, instead of only outcomes, (4) making model application more flexible and robust, and (5) increasing support for self-explanation and user interaction with the meta-level.

Subjects: 12. Machine Learning and Discovery; 3. Automated Reasoning

Submitted: May 5, 2008

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.