TY - JOUR
T1 - Domain transfer via cross-domain analogy
AU - Klenk, Matthew
AU - Forbus, Kenneth D
N1 - Funding Information:
This research was supported by the Cognitive Science Program of the Office of Naval Research. The authors would like to thank the participants of the AnICA 2007 workshop for the helpful feedback on the ideas presented here. Also, we thank Thomas Hinrichs, Kate Lockwood, and Scott Friedman for their comments on this work and help revising this document.
Copyright:
Copyright 2009 Elsevier B.V., All rights reserved.
PY - 2009/9
Y1 - 2009/9
N2 - Analogical learning has long been seen as a powerful way of extending the reach of one's knowledge. We present the domain transfer via analogy (DTA) method for learning new domain theories via cross-domain analogy. Our model uses analogies between pairs of textbook example problems, or worked solutions, to create a domain mapping between a familiar and a new domain. This mapping allows us to initialize a new domain theory. After this initialization, another analogy is made between the domain theories themselves, providing additional conjectures about the new domain. We present two experiments in which our model learns rotational kinematics by an analogy with translational kinematics, and vice versa. These learning rates outperform those from a version of the system that is incrementally given the correct domain theory.
AB - Analogical learning has long been seen as a powerful way of extending the reach of one's knowledge. We present the domain transfer via analogy (DTA) method for learning new domain theories via cross-domain analogy. Our model uses analogies between pairs of textbook example problems, or worked solutions, to create a domain mapping between a familiar and a new domain. This mapping allows us to initialize a new domain theory. After this initialization, another analogy is made between the domain theories themselves, providing additional conjectures about the new domain. We present two experiments in which our model learns rotational kinematics by an analogy with translational kinematics, and vice versa. These learning rates outperform those from a version of the system that is incrementally given the correct domain theory.
KW - Cross-domain analogy
KW - Learning
UR - http://www.scopus.com/inward/record.url?scp=67349288541&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=67349288541&partnerID=8YFLogxK
U2 - 10.1016/j.cogsys.2008.09.005
DO - 10.1016/j.cogsys.2008.09.005
M3 - Article
AN - SCOPUS:67349288541
VL - 10
SP - 240
EP - 250
JO - Cognitive Systems Research
JF - Cognitive Systems Research
SN - 1389-0417
IS - 3
ER -