Multistrategy Task-adaptive Learning Using Dynamically Interlaced Hierarchies: A Methodology and Initial Implementation of INTERLACE

Nabil W. Alkharouf and Ryszard S. Michalski

This research concerns the development of a methodology for representing, planning and executing multitype inferences in a multistrategy task-adaptive learning system. These inferences, defined in the Inferential Theory of Learning as knowledge transmutations, are generic types of knowledge operators, and are assumed to underlie all learning processes. The paper shows how several basic knowledge transmutations can be seamlessly integrated using a knowledge representation based on dynamic interlaced hierarchies (DIH). The implemented system, INTERLACE, includes an interactive graphical user interface for visualizing knowledge transmutations that are being performed by the system. INTERLACE is illustrated by several examples.


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.