|
|
|
|
| LEADER |
01471 am a22002173u 4500 |
| 001 |
112784 |
| 042 |
|
|
|a dc
|
| 100 |
1 |
0 |
|a Kemp, Charles
|e author
|
| 100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
|e contributor
|
| 100 |
1 |
0 |
|a Kemp, Charles
|e contributor
|
| 100 |
1 |
0 |
|a Goodman, Noah Daniel
|e contributor
|
| 100 |
1 |
0 |
|a Tenenbaum, Joshua B
|e contributor
|
| 700 |
1 |
0 |
|a Goodman, Noah Daniel
|e author
|
| 700 |
1 |
0 |
|a Tenenbaum, Joshua B
|e author
|
| 245 |
0 |
0 |
|a Learning and using relational theories
|
| 260 |
|
|
|b Neural Information Processing Systems Foundation,
|c 2017-12-18T15:55:09Z.
|
| 856 |
|
|
|z Get fulltext
|u http://hdl.handle.net/1721.1/112784
|
| 520 |
|
|
|a Kemp, Charles; Goodman, Noah D.; Tenenbaum, Joshua B.
|
| 520 |
|
|
|a 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 provides a better account of human learning and reasoning than an approach developed by Goodman [1] .
|
| 655 |
7 |
|
|a Article
|
| 773 |
|
|
|t Advances in Neural Information Processing Systems (NIPS)
|
