TY - GEN
T1 - Constructing Hierarchical Concepts via Analogical Generalization
AU - Liang, C.
AU - Forbus, K.
N1 - Funding Information:
This research was sponsored by the Socio-Cognitive Architectures for Adaptable Autonomous Systems Program of the Office of Naval Research, N00014-13-1-0470.
Publisher Copyright:
© 2014 Proceedings of the 36th Annual Meeting of the Cognitive Science Society, CogSci 2014. All rights reserved.
PY - 2014
Y1 - 2014
N2 - Learning hierarchical concepts is a central problem in cognitive science. This paper explores the Nearest-Merge algorithm for creating hierarchical clusters that can handle both feature-based and relational information, building on the SAGE model of analogical generalization. We describe its results on three data sets, showing that it provides reasonable fits with human data and comparable results to Bayesian models.
AB - Learning hierarchical concepts is a central problem in cognitive science. This paper explores the Nearest-Merge algorithm for creating hierarchical clusters that can handle both feature-based and relational information, building on the SAGE model of analogical generalization. We describe its results on three data sets, showing that it provides reasonable fits with human data and comparable results to Bayesian models.
KW - Analogy
KW - computational modeling
KW - concept learning
KW - hierarchical clustering
UR - http://www.scopus.com/inward/record.url?scp=85028718463&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85028718463&partnerID=8YFLogxK
M3 - Conference contribution
T3 - Proceedings of the 36th Annual Meeting of the Cognitive Science Society, CogSci 2014
SP - 2561
EP - 2566
BT - Proceedings of the 36th Annual Meeting of the Cognitive Science Society, CogSci 2014
PB - The Cognitive Science Society
T2 - 36th Annual Meeting of the Cognitive Science Society, CogSci 2014
Y2 - 23 July 2014 through 26 July 2014
ER -