LEADER 03597oam 2200661Ia 450 001 9910777833803321 005 20190503073338.0 010 $a1-282-09635-4 010 $a9786612096358 010 $a0-262-25629-0 010 $a1-4294-6560-3 035 $a(CKB)1000000000472548 035 $a(EBL)3338578 035 $a(SSID)ssj0000203321 035 $a(PQKBManifestationID)11173175 035 $a(PQKBTitleCode)TC0000203321 035 $a(PQKBWorkID)10258548 035 $a(PQKB)10603354 035 $a(MiAaPQ)EBC3338578 035 $a(CaBNVSL)mat06267274 035 $a(IDAMS)0b000064818b4260 035 $a(IEEE)6267274 035 $a(OCoLC)123173836$z(OCoLC)228170833$z(OCoLC)228170835$z(OCoLC)473752043$z(OCoLC)568000642$z(OCoLC)648225222$z(OCoLC)722565236$z(OCoLC)756542008$z(OCoLC)815786487$z(OCoLC)888592557$z(OCoLC)961581303$z(OCoLC)962619962$z(OCoLC)988440183$z(OCoLC)991951887$z(OCoLC)991955916$z(OCoLC)1037500070$z(OCoLC)1037941140$z(OCoLC)1038657196$z(OCoLC)1055393012$z(OCoLC)1062885916$z(OCoLC)1081259182$z(OCoLC)1083560664 035 $a(OCoLC-P)123173836 035 $a(MaCbMITP)4643 035 $a(Au-PeEL)EBL3338578 035 $a(CaPaEBR)ebr10173636 035 $a(CaONFJC)MIL209635 035 $a(OCoLC)123173836 035 $a(EXLCZ)991000000000472548 100 $a20070417d2007 uy 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 14$aThe minimum description length principle /$fPeter D. Gru?nwald 210 $aCambridge, Mass. $cMIT Press$dİ2007 215 $a1 online resource (736 p.) 225 1 $aAdaptive computation and machine learning 300 $aDescription based upon print version of record. 311 $a0-262-07281-5 320 $aIncludes bibliographical references (p. [651]-673) and indexes. 327 $aContents; 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 Complexity 327 $a12 - 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 Index 330 $aA comprehensive introduction and reference guide to the minimum description length (MDL) Principle that is accessible to researchers dealing with inductive reference in diverse areas including statistics, pattern classification, machine learning, data min. 410 0$aAdaptive computation and machine learning. 606 $aMinimum description length (Information theory) 610 $aCOMPUTER SCIENCE/Machine Learning & Neural Networks 615 0$aMinimum description length (Information theory) 676 $a003/.54 700 $aGru?nwald$b Peter D$0601519 801 0$bOCoLC-P 801 1$bOCoLC-P 906 $aBOOK 912 $a9910777833803321 996 $aMinimum description length principle$91020915 997 $aUNINA