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...
Saved in:
| Published in: | Current opinion in behavioral sciences Vol. 29; pp. 117 - 126 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Ltd
01.10.2019
|
| ISSN: | 2352-1546, 2352-1554 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | •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. |
|---|---|
| Bibliography: | 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 |