On-Line Learning in Neural Networks

David Saad

ISBN 10: 0521652634 / ISBN 13: 9780521652636

Edité par Cambridge University Press, 1999

A propos de cet article

Druck auf Anfrage Neuware - Printed after ordering - Edited volume written by leading experts providing state-of-art survey in on-line learning and neural networks.

N° de réf. du vendeur 9780521652636

Détails bibliographiques

• Titre: On-Line Learning in Neural Networks
• Éditeur: Cambridge University Press
• Date de parution: 1999
• Langue: anglais
• ISBN à 10 chiffres: 0521652634
• ISBN à 13 chiffres: 9780521652636
• Reliure: Buch
• État de l'article: Neu
• Dimensions: 235 L x 157 H x 29 P (en millimètres) 235 millimètres de largeur par 157 millimètres de hauteur par 29 millimètres de profondeur
• Poids: 817 grammes

A propos de ce titre

Synopsis

Edited volume written by leading experts providing state-of-art survey in on-line learning and neural networks.

Présentation de l'éditeur

On-line learning is one of the most powerful and commonly used techniques for training large layered networks and has been used successfully in many real-world applications. Traditional analytical methods have been recently complemented by ones from statistical physics and Bayesian statistics. This powerful combination of analytical methods provides more insight and deeper understanding of existing algorithms and leads to novel and principled proposals for their improvement. This book presents a coherent picture of the state-of-the-art in the theoretical analysis of on-line learning. An introduction relates the subject to other developments in neural networks and explains the overall picture. Surveys by leading experts in the field combine new and established material and enable non-experts to learn more about the techniques and methods used. This book, the first in the area, provides a comprehensive view of the subject and will be welcomed by mathematicians, scientists and engineers, whether in industry or academia.