English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Formalizing Neurath’s ship: Approximate algorithms for online causal learning

Bramley, N., Dayan, P., Griffiths, T., & Lagnado, D. (2017). Formalizing Neurath’s ship: Approximate algorithms for online causal learning. Psychological Review, 124(3), 301-338. doi:10.1037/rev0000061.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0002-C23E-E Version Permalink: http://hdl.handle.net/21.11116/0000-0002-C23F-D
Genre: Journal Article

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Bramley, NR, Author
Dayan, P1, Author              
Griffiths, TL, Author
Lagnado, DA, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Higher-level cognition depends on the ability to learn models of the world. We can characterize this at the computational level as a structure-learning problem with the goal of best identifying the prevailing causal relationships among a set of relata. However, the computational cost of performing exact Bayesian inference over causal models grows rapidly as the number of relata increases. This implies that the cognitive processes underlying causal learning must be substantially approximate. A powerful class of approximations that focuses on the sequential absorption of successive inputs is captured by the Neurath’s ship metaphor in philosophy of science, where theory change is cast as a stochastic and gradual process shaped as much by people’s limited willingness to abandon their current theory when considering alternatives as by the ground truth they hope to approach. Inspired by this metaphor and by algorithms for approximating Bayesian inference in machine learning, we propose an algorithmic-level model of causal structure learning under which learners represent only a single global hypothesis that they update locally as they gather evidence. We propose a related scheme for understanding how, under these limitations, learners choose informative interventions that manipulate the causal system to help elucidate its workings. We find support for our approach in the analysis of 3 experiments.

Details

show
hide
Language(s):
 Dates: 2017-04
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1037/rev0000061
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Psychological Review
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Washington, etc. : American Psychological Association (PsycARTICLES)
Pages: - Volume / Issue: 124 (3) Sequence Number: - Start / End Page: 301 - 338 Identifier: ISSN: 0033-295X
CoNE: https://pure.mpg.de/cone/journals/resource/954925436473