Description

Learning and Generalization provides a formal mathematical theory for addressing intuitive questions such as:

• How does a machine learn a new concept on the basis of examples?

• How can a neural network, after sufficient training, correctly predict the outcome of a previously unseen input?

• How much training is required to achieve a specified level of accuracy in the prediction?

• How can one identify the dynamical behaviour of a nonlinear control system by observing its input-output behaviour over a finite interval of time?

In its successful first edition, A Theory of Learning and Generalization was the first book to treat the problem of machine learning in conjunction with the theory of empirical processes, the latter being a well-established branch of probability theory. The treatment of both topics side-by-side leads to new insights, as well as to new results in both topics.

This second edition extends and improves upon this material, covering new areas including:

• Support vector machines.

• Fat-shattering dimensions and applications to neural network learning.

• Learning with dependent samples generated by a beta-mixing process.

• Connections between system identification and learning theory.

• Probabilistic solution of ‘intractable problems’ in robust control and matrix theory using randomized algorithm.

Reflecting advancements in the field, solutions to some of the open problems posed in the first edition are presented, while new open problems have been added.

Learning and Generalization (second edition) is essential reading for control and system theorists, neural network researchers, theoretical computer scientists and probabilist.

Langue

en

Version

Broché

Date de sortie initiale

19 octobre 2010

Nombre de pages

488

Illustrations

Non

Personnes impliquées

Auteur principal

Mathukumalli Vidyasagar

Deuxième auteur

M. Vidyasagar

Editeur principal

Springer

Informations sur le fabricant

Nom du fabricant

Springer Nature Customer Service Center GmbH

Adresse du fabricant

Europaplatz 3 | 69115| Heidelberg| DE

Adresse électronique du fabricant

[email protected]

Informations sur le fabricant

Les informations du fabricant ne sont actuellement pas disponibles

Autres spécifications

Hauteur de l’emballage

26 mm

Largeur d’emballage

155 mm

Largeur du produit

155 mm

Longueur d’emballage

235 mm

Longueur du produit

235 mm

Poids de l’emballage

783 g

Police de caractères extra large

Non

Édition

2

EAN

EAN

9781849968676

Sécurité des produits

Opérateur économique responsable dans l’UE

Afficher les données

Vous trouverez cet article :

Catégories

Technologie et architecture

Ordinateurs et Informatique

Technologies informatiques

Technologie de l’énergie

Intelligence artificielle

Électrotechnique

Apprentissage automatique

Réseaux de neurones et systèmes flous

Livres

Livre, ebook ou livre audio ?

Livre

Disponibilité

Disponible à l’adresse suivante

Langue

Anglais

Type de livre

Paperback