Learning to Learn Functions
Cognitive Science · 2023-04 · 47 (4)
DOI: 10.1111/cogs.13262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cognitive Science, online erschienen am 13.04.2023. Verfasst von Michael Y Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Stanford University. Hauptthemen laut MEDLINE: Learning, Models, Psychological. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Humans can learn complex functional relationships between variables from small amounts of data. In doing so, they draw on prior expectations about the form of these relationships. In three experiments, we show that people learn to adjust these expectations through experience, learning about the likely forms of the functions they will encounter. Previous work has used Gaussian processes—a statistical framework that extends Bayesian nonparametric approaches to regression—to model human function learning. We build on this work, modeling the process of learning to learn functions as a form of hierarchical Bayesian inference about the Gaussian process hyperparameters.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science, Stanford University.
- Department of Psychology, Princeton University.
- Department of Computer Science, Princeton University.
Zitieren
APA
Li, M. Y., Callaway, F., Thompson, W. D., Adams, R. P., & Griffiths, T. L. (2023). Learning to Learn Functions. Cognitive Science, 47(4). https://doi.org/10.1111/cogs.13262
Vancouver
Li MY, Callaway F, Thompson WD, Adams RP, Griffiths TL. Learning to Learn Functions. Cognitive Science. 2023;47(4). doi:10.1111/cogs.13262
BibTeX
@article{Li2023,
author = {Li, Michael Y and Callaway, Fred and Thompson, William D and Adams, Ryan P and Griffiths, Thomas L},
title = {Learning to Learn Functions},
journal = {Cognitive Science},
year = {2023},
volume = {47},
number = {4},
doi = {10.1111/cogs.13262}
}
EUVIMED