03597oam 2200661Ia 450 991077783380332120190503073338.01-282-09635-497866120963580-262-25629-01-4294-6560-3(CKB)1000000000472548(EBL)3338578(SSID)ssj0000203321(PQKBManifestationID)11173175(PQKBTitleCode)TC0000203321(PQKBWorkID)10258548(PQKB)10603354(MiAaPQ)EBC3338578(CaBNVSL)mat06267274(IDAMS)0b000064818b4260(IEEE)6267274(OCoLC)123173836(OCoLC)228170833(OCoLC)228170835(OCoLC)473752043(OCoLC)568000642(OCoLC)648225222(OCoLC)722565236(OCoLC)756542008(OCoLC)815786487(OCoLC)888592557(OCoLC)961581303(OCoLC)962619962(OCoLC)988440183(OCoLC)991951887(OCoLC)991955916(OCoLC)1037500070(OCoLC)1037941140(OCoLC)1038657196(OCoLC)1055393012(OCoLC)1062885916(OCoLC)1081259182(OCoLC)1083560664(OCoLC-P)123173836(MaCbMITP)4643(Au-PeEL)EBL3338578(CaPaEBR)ebr10173636(CaONFJC)MIL209635(OCoLC)123173836(EXLCZ)99100000000047254820070417d2007 uy 0engur|n|---|||||txtccrThe minimum description length principle /Peter D. GrünwaldCambridge, Mass. MIT Press©20071 online resource (736 p.)Adaptive computation and machine learningDescription based upon print version of record.0-262-07281-5 Includes bibliographical references (p. [651]-673) and indexes.Contents; List of Figures; Series Foreword; Foreword; Preface; PART I - Introductory Material; 1 - Learning, Regularity, and Compression; 2 - Probabilistic and Statistical Preliminaries; 3 - Information-Theoretic Preliminaries; 4 - Information-Theoretic Properties of Statistical Models; 5 - Crude Two-Part Code MDL; PART II - Universal Coding; 6 - Universal Coding with Countable Models; 7 - Parametric Models: Normalized Maximum Likelihood; 8 - Parametric Models: Bayes; 9 - Parametric Models: Prequential Plug-in; 10 - Parametric Models: Two-Part; 11 - NMLWith Innite Complexity12 - Linear RegressionPART III - Refined MDL; 14 - MDL Model Selection; 15 - MDL Prediction and Estimation; 16 - MDL Consistency and Convergence; 17 - MDL in Context; PART IV - Additional Background; 18 - The Exponential or "Maximum Entropy" Families; 19 - Information-Theoretic Properties of Exponential Families; References; List of Symbols; Subject IndexA comprehensive introduction and reference guide to the minimum description length (MDL) Principle that is accessible to researchers dealing with inductive reference in diverse areas including statistics, pattern classification, machine learning, data min.Adaptive computation and machine learning.Minimum description length (Information theory)COMPUTER SCIENCE/Machine Learning & Neural NetworksMinimum description length (Information theory)003/.54Grünwald Peter D601519OCoLC-POCoLC-PBOOK9910777833803321Minimum description length principle1020915UNINA