Learning Structured Generative Concepts
Many real world concepts, such as “car”, “house”, and “tree”, are more than simply a collection of features. These objects are richly structured, defined in terms of systems of relations, subparts, and recursive embeddings. We describe an approach to concept representation and learning that att...
Main Authors: | Stuhlmuller, Andreas, Tenenbaum, Joshua B, Goodman, Noah Daniel |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences |
Format: | Article |
Published: |
Cognitive Science Society
2017
|
Online Access: | http://hdl.handle.net/1721.1/112758 https://orcid.org/0000-0002-1925-2035 |
Similar Items
-
Learning physical parameters from dynamic scenes
by: Ullman, Tomer D., et al.
Published: (2020) -
Beyond Boolean logic: exploring representation languages for learning complex concepts
by: Piantadosi, Steven Thomas, et al.
Published: (2017) -
Concepts in a Probabilistic Language of Thought
by: Goodman, Noah D., et al.
Published: (2015) -
Compositionality in rational analysis: Grammar-based induction for concept learning
by: Goodman, Noah D., et al.
Published: (2020) -
Learning and using relational theories
by: Kemp, Charles, et al.
Published: (2017)