Premium
Embedding Bayes' theorem in general learning rules: Connections between idealized behaviour and empirical research on learning
Author(s) -
Lad Frank
Publication year - 1978
Publication title -
british journal of mathematical and statistical psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.157
H-Index - 51
eISSN - 2044-8317
pISSN - 0007-1102
DOI - 10.1111/j.2044-8317.1978.tb00579.x
Subject(s) - bayes' theorem , bayesian probability , class (philosophy) , embedding , artificial intelligence , machine learning , computer science , basis (linear algebra) , bayesian inference , bayes estimator , decision rule , mathematics , mathematical economics , geometry
A response is made to the recent discussions critical of the Bayesian learning procedure on the basis of empirically observed deviations from its prescriptions. Bayes' theorem is embedded in a more general class of learning rules which allow for departure from the demands of idealized rational behaviour. Such departures are termed learning impediments or disabilities. Some particular forms and interpretations of impediment functions are presented. Consequences of learning disabilities for the likelihood principle, stable estimation and admissible decision‐making are explored. Examples of surprising learning behaviours and decision strategies are generated. Deeper understanding of Bayesian learning and its characteristics results.