Simple trees in complex forests: Growing Take The Best by Approximate Bayesian 
Computation

Schulz, E; Speekenbrink, M; Meder, B

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Conference Paper

Simple trees in complex forests: Growing Take The Best by Approximate Bayesian Computation

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

https://ericschulz.github.io/publications/Schulz2016trees.pdf
(Any fulltext)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Schulz, E., Speekenbrink, M., & Meder, B. (2017). Simple trees in complex forests: Growing Take The Best by Approximate Bayesian Computation. In A. Papafragou, D. Grodner, D. Mirman, & J. Trueswell (Eds.), 38th Annual Meeting of the Cognitive Science Society (CogSci 2016): Recognizing and Representing Events (pp. 2531-2536). Red Hook, NY, USA: Curran.

Cite as: https://hdl.handle.net/21.11116/0000-0006-B427-3

Abstract

How can heuristic strategies emerge from smaller building blocks? We propose Approximate Bayesian Computation as a computational solution to this problem. As a first proof of concept, we demonstrate how a heuristic decision strategy such as Take The Best (TTB) can be learned from smaller, probabilistically updated building blocks. Based on a self-reinforcing sampling scheme, different building blocks are combined and, over time, tree-like non-compensatory heuristics emerge. This new algorithm, coined Approximately Bayesian Computed Take The Best (ABC-TTB), is able to recover a data set that was generated by TTB, leads to sensible inferences about cue importance and cue directions, can outperform traditional TTB, and allows to trade-off performance and computational effort explicitly.