Persistent Mappings in Cross-Domain Analogical Learning of Physics Domains
Abstract
Cross-domain analogies are a powerful method for learning new domains. This paper extends the Domain Transfer via Analogy (DTA) method with the idea of persistent mappings, correspondences between domains that are incrementally built up as a system gains experience with a new domain. We evaluate DTA plus persistent mappings by learning three domains (rotational mechanics, electricity, and heat) by analogy with linear mechanics, showing that persistent mappings improves performance.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2009
- Accession Number
- ADA501855
Entities
People
- Ken Forbus
- Matthew Klenk