The Generalization Artist - Or: How Can We Characterize Human Generalization?

Abstract excerpt

<p>A common understanding is that people are generalization artists: they require far fewer experience to generalize their knowledge when compared to contemporary AI systems, i.e. deep neural network models. Here, we summarize evidence in favor and against this notion. We propose three stages, determining how people generalize. First, people must infer what aspects of an environment are relevant for a task. Second...

Topics

Open a Topic to create a Post that cites this publication.

• Uncategorized literature

Identifiers and source

Literature Corpus work

705c22e8-592b-5a9d-91e7-532170384fad

DOI

10.31234/osf.io/k6ect