Theory of Neural Information Processing Systems

Coolen, A.C.C.; Kuehn, R.; Sollich, P.

ISBN 10: 0198530242 / ISBN 13: 9780198530244

Edité par Oxford University Press, 2005

N° de réf. du vendeur 9780198530244

Synopsis :

This interdisciplinary graduate text gives a full, explicit, coherent and up-to-date account of the modern theory of neural information processing systems and is aimed at student with an undergraduate degree in any quantitative discipline (e.g. computer science, physics, engineering, biology, or mathematics). The book covers all the major theoretical developments from the 1940s tot he present day, using a uniform and rigorous style of presentation and of mathematical notation. The text starts with simple model neurons and moves gradually to the latest advances in neural processing. An ideal textbook for postgraduate courses in artificial neural networks, the material has been class-tested. It is fully self contained and includes introductions to the various discipline-specific mathematical tools as well as multiple exercises on each topic.

Présentation de l'éditeur: Theory of Neural Information Processing Systems provides an explicit, coherent, and up-to-date account of the modern theory of neural information processing systems. It has been carefully developed for graduate students from any quantitative discipline, including mathematics, computer science, physics, engineering or biology, and has been thoroughly class-tested by the authors over a period of some 8 years. Exercises are presented throughout the text and notes on historical background and further reading guide the student into the literature. All mathematical details are included and appendices provide further background material, including probability theory, linear algebra and stochastic processes, making this textbook accessible to a wide audience.

Détails bibliographiques

Titre : Theory of Neural Information Processing ...
Éditeur : Oxford University Press
Date d'édition : 2005
Reliure : Couverture souple
Etat : Usado - bueno