The minimum description length principle /

Show other versions (1)

A 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.

Bibliographic Details
Call Number:Libro Electrónico
Main Author: Grünwald, Peter D.
Format: Electronic eBook
Language:Inglés
Published: Cambridge, Mass. : MIT Press, ©2007.
Series:Adaptive computation and machine learning.
Subjects:
Minimum description length (Information theory)
Longueur de description minimale (Théorie de l'information)
COMPUTERS > Information Theory.
COMPUTER SCIENCE/Machine Learning & Neural Networks
Online Access:Texto completo
Table of 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 Complexity.
  • 12
  • 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.

Similar Items