Timezone: »

 
Spotlight
Abstraction and Relational learning
Charles Kemp · Alan Jern

Tue Dec 08 03:28 PM -- 03:29 PM (PST) @ None

Many categories are better described by providing relational information than listing characteristic features. We present a hierarchical generative model that helps to explain how relational categories are learned and used. Our model learns abstract schemata that specify the relational similarities shared by members of a category, and our emphasis on abstraction departs from previous theoretical proposals that focus instead on comparison of concrete instances. Our first experiment suggests that our abstraction-based account can address some of the tasks that have previously been used to support comparison-based approaches. Our second experiment focuses on one-shot schema learning, a problem that raises challenges for comparison-based approaches but is handled naturally by our abstraction-based account.

Author Information

Charles Kemp (Carnegie Mellon University)
Alan Jern (Rose-Hulman Institute of Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors