A learning criterion for stochastic rules

zbMath0766.68117MaRDI QIDQ1207304

Kenji Yamanishi

Publication date: 1 April 1993

Published in: Machine Learning (Search for Journal in Brave)

zbMATH Keywords

minimum description length principlesample complexitylearning from examplesPAC learning modelstochastic decision listsstochastic decision treesstochastic rules

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (9)

Efficient distribution-free learning of probabilistic concepts ⋮ High-dimensional penalty selection via minimum description length principle ⋮ Toward efficient agnostic learning ⋮ Stochastic complexity in learning ⋮ Learning about the parameter of the Bernoulli model ⋮ On-line maximum likelihood prediction with respect to general loss functions ⋮ The role of mutual information in variational classifiers ⋮ The decomposed normalized maximum likelihood code-length criterion for selecting hierarchical latent variable models ⋮ Links between probabilistic automata and hidden Markov models: probability distributions, learning models and induction algorithms

This page was built for publication: A learning criterion for stochastic rules