What is optimal in optimal inference?

Gaia Tavoni, Vijay Balasubramanian, Joshua I. Gold

Research output: Contribution to journalReview articlepeer-review

1 Scopus citations

Abstract

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.

Original languageEnglish
Pages (from-to)117-126
Number of pages10
JournalCurrent Opinion in Behavioral Sciences
Volume29
DOIs
StatePublished - Oct 2019

Fingerprint

Dive into the research topics of 'What is optimal in optimal inference?'. Together they form a unique fingerprint.

Cite this