Carnegie Mellon University
file.pdf (197.65 kB)
Download file

Learning and using relational theories

Download (197.65 kB)
journal contribution
posted on 2007-12-01, 00:00 authored by Charles KempCharles Kemp, Noah D. Goodman, Joshua B. Tenenbaum

Much of human knowledge is organized into sophisticated systems that are often called intuitive theories. We propose that intuitive theories are mentally represented in a logical language, and that the subjective complexity of a theory is determined by the length of its representation in this language. This complexity measure helps to explain how theories are learned from relational data, and how they support inductive inferences about unobserved relations. We describe two experiments that test our approach, and show that it provide s a better account of human learning and reasoning than an approach developed by Goodman [1]




Usage metrics