PAC-Bayesian pattern classification with kernels. Theory, algorithms, and an application to the game Go.

MaRDI QIDQ5481248zbMATH OpenFDO

Authors Thore Graepel

Publication date 9 August 2006

Full work available at URL http://opus.kobv.de/tuberlin/frontdoor.php?source_opus=344

Mathematics Subject Classification ID

Bayesian inference (62F15) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Game theory (91A99)

Recommendations

• scientific article; zbMATH DE number 1843056
• Learning to score final positions in the game of Go
• scientific article
• PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification
• PAC-Bayesian compression bounds on the prediction error of learning algorithms for classification

Cited in

(4)

• scientific article; zbMATH DE number 1843056 (Why is no real title available?)
• A pattern classification approach to evaluation function learning
• Graph kernels and Gaussian processes for relational reinforcement learning
• Learning to score final positions in the game of Go

This page was built for publication: PAC-Bayesian pattern classification with kernels. Theory, algorithms, and an application to the game Go.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5481248)