undrgrnd Cliquez ici NEWNEEEW nav-sa-clothing-shoes Cloud Drive Photos FIFA16 cliquez_ici Rentrée scolaire Shop Fire HD 6 Shop Kindle Paperwhite cliquez_ici Jeux Vidéo Bijoux Montres Montres
EUR 48,02
  • Tous les prix incluent la TVA.
Il ne reste plus que 1 exemplaire(s) en stock (d'autres exemplaires sont en cours d'acheminement).
Expédié et vendu par Amazon.
Emballage cadeau disponible.
Quantité :1
The Minimum Description L... a été ajouté à votre Panier
Vous l'avez déjà ?
Repliez vers l'arrière Repliez vers l'avant
Ecoutez Lecture en cours... Interrompu   Vous écoutez un extrait de l'édition audio Audible
En savoir plus
Voir cette image

The Minimum Description Length Principle (Anglais) Relié – 8 mai 2007


Voir les formats et éditions Masquer les autres formats et éditions
Prix Amazon Neuf à partir de Occasion à partir de
Relié
"Veuillez réessayer"
EUR 48,02
EUR 36,53 EUR 41,13

Livres anglais et étrangers
Lisez en version originale. Cliquez ici

Offres spéciales et liens associés


Descriptions du produit

The Minimum Description Length Principle A comprehensive introduction and reference guide to the minimum description length (MDL) Principle that is useful for researchers dealing with inductive reference in diverse areas including statistics, pattern classification, machine learning, data mining, biology, econometrics, and experimental psychology. Full description



Détails sur le produit


En savoir plus sur l'auteur

Découvrez des livres, informez-vous sur les écrivains, lisez des blogs d'auteurs et bien plus encore.

Dans ce livre

(En savoir plus)
En découvrir plus
Concordance
Parcourir les pages échantillon
Couverture | Copyright | Table des matières | Extrait | Index
Rechercher dans ce livre:

Commentaires en ligne

Il n'y a pas encore de commentaires clients sur Amazon.fr
5 étoiles
4 étoiles
3 étoiles
2 étoiles
1 étoiles

Commentaires client les plus utiles sur Amazon.com (beta)

Amazon.com: 2 commentaires
14 internautes sur 15 ont trouvé ce commentaire utile 
An excellent, deep summary of MDL theory. 20 octobre 2007
Par Someone - Publié sur Amazon.com
Format: Relié
This book provides an excellent, in-depth summary of current MDL theory. It is arguably the best text on the topic of MDL currently written, and is one of the best expositions of a general approach to statistical inference more broadly.

One of the greatest strengths of the text is its ability to start from basics of probability and work toward profound insights into statistical inference, without sacrificing important mathematical detail. Grunwald does a good job of explaining the MDL paradigm and how it is related to more traditional paradigms--especially the Bayesian paradigm--while acknowledging current limitations in our understanding of MDL inference.

This text has much to offer those already familiar with MDL, however, and serves as much more than an introduction to the topic. Grunwald provides an excellent summary of important but lesser-known information-theoretic results that are critical to MDL and statistical inference more broadly. He also provides an excellent summary of current problems facing the field, which can be helpful even among those who are already aware of them.

Although excellent, the text is not perfect of course. Grunwald's tone is sometimes overly antagonistic towards critics, and he has a tendency to overstate the seriousness of relatively trivial problems, some of which apply to any inference paradigm. I also would have preferred more discussion of relationships between MDL and the frequentist paradigm, as there is much there to explore, especially in the domain of exact methods.

The text can be mathematically intense at times, but not inappropriately so, being a book on a major theory of statistical inference. I was actually impressed at the extent to which major theorems were gradually built up from extraordinarily basic mathematical principles.

In general, I would highly recommend this text to anyone interested in general principles of statistical inference or information theory. Although the book is on a particular approach to statistical inference, using a particular branch of information theory (i.e., optimal inference is based on choosing models that result in the most parsimonious information-theoretic description of the data and model), it has implications and utility in a number of fields.
3 internautes sur 17 ont trouvé ce commentaire utile 
VERY heavy on theory & math 1 septembre 2007
Par G. Caprio - Publié sur Amazon.com
Format: Relié Achat vérifié
This book is provides a good overview to the theory behind MDL. Not for the faint of heart, however.
Ces commentaires ont-ils été utiles ? Dites-le-nous

Rechercher des articles similaires par rubrique


Commentaires

Souhaitez-vous compléter ou améliorer les informations sur ce produit ? Ou faire modifier les images?