Learning How to Generalize

Cognitive Science 43 (8):e12777 (2019)
  Copy   BIBTEX


Generalization is a fundamental problem solved by every cognitive system in essentially every domain. Although it is known that how people generalize varies in complex ways depending on the context or domain, it is an open question how people learn the appropriate way to generalize for a new context. To understand this capability, we cast the problem of learning how to generalize as a problem of learning the appropriate hypothesis space for generalization. We propose a normative mathematical framework for learning how to generalize by learning inductive biases for which properties are relevant for generalization in a domain from the statistical structure of features and concepts observed in that domain. More formally, the framework predicts that an ideal learner should learn to generalize by either taking the weighted average of the results of generalizing according to each hypothesis space, with weights given by how well each hypothesis space fits the previously observed concepts, or by using the most likely hypothesis space. We compare the predictions of this framework to human generalization behavior with three experiments in one perceptual (rectangles) and two conceptual (animals and numbers) domains. Across all three studies we find support for the framework's predictions, including individual‐level support for averaging in the third study.



    Upload a copy of this work     Papers currently archived: 92,038

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Logically reliable inductive inference.Oliver Schulte - 2007 - In Friend Michele, Goethe Norma B. & Harizanov Valentina (eds.), Induction, algorithmic learning theory, and philosophy. Springer. pp. 157-178.
Evolving to Generalize: Trading Precision for Speed.Cailin O’Connor - 2017 - British Journal for the Philosophy of Science 68 (2).
The complexity of learning SUBSEQ(A).Stephen Fenner, William Gasarch & Brian Postow - 2009 - Journal of Symbolic Logic 74 (3):939-975.


Added to PP

16 (#907,699)

6 months
3 (#978,358)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Tom Griffiths
Aarhus University