Learning overhypotheses

Files

hdl_65716.pdf (214.28 KB)
  (Published version)

Date

2006

Authors

Kemp, C.
Perfors, A.
Tenenbaum, J.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the 28th Annual Conference of the Cognitive Science Society (CogSci 2006) / R. Sun and N. Miyake (eds.), 26-29 July, 2006; pp.417-422

Statement of Responsibility

Charles Kemp, Amy Perfors and Joshua B. Tenenbaum

Conference Name

Annual Conference of the Cognitive Science Society (28th : 2006 : Vancouver, Canada)

Abstract

Inductive learning is impossible without overhypothe-ses, or constraints on the hypotheses considered by the learner. Some of these overhypotheses must be innate, but we suggest that hierarchical Bayesian models help explain how the rest can be acquired. The hierarchi-cal approach also addresses a common question about Bayesian models of cognition: where do the priors come from? To illustrate our claims, we consider two specific kinds of overhypotheses — overhypotheses about fea-ture variability (e.g. the shape bias in word learning) and overhypotheses about the grouping of categories into on-tological kinds like objects and substances.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© the authors

License

Grant ID

Call number

Persistent link to this record