What is optimal in optimal inference?

•Brains and machines solve inference problems subject to constraints.•These constraints include limits on information and computing resources.•To account for these constraints, optimality can be assessed as benefits per unit cost. Inferring hidden structure from noisy observations is a problem addre...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Current opinion in behavioral sciences Jg. 29; S. 117 - 126
Hauptverfasser: Tavoni, Gaia, Balasubramanian, Vijay, Gold, Joshua I
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.10.2019
ISSN:2352-1546, 2352-1554
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•Brains and machines solve inference problems subject to constraints.•These constraints include limits on information and computing resources.•To account for these constraints, optimality can be assessed as benefits per unit cost. Inferring hidden structure from noisy observations is a problem addressed by Bayesian statistical learning, which aims to identify optimal models of the process that generated the observations given assumptions that constrain the space of potential solutions. Animals and machines face similar “model-selection” problems to infer latent properties and predict future states of the world. Here we review recent attempts to explain how intelligent agents address these challenges and how their solutions relate to Bayesian principles. We focus on how constraints on available information and resources affect inference and propose a general framework that uses benefit versus accuracy and accuracy versus cost curves to assess optimality under these constraints.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2352-1546
2352-1554
DOI:10.1016/j.cobeha.2019.07.008