Tous nos rayons

Déjà client ? Identifiez-vous

Mot de passe oublié ?

Nouveau client ?

CRÉER VOTRE COMPTE
Object-Oriented Neural Networks in C++
Ajouter à une liste

Librairie Eyrolles - Paris 5e
Indisponible

Object-Oriented Neural Networks in C++

Object-Oriented Neural Networks in C++

Joey Rogers

310 pages, parution le 10/10/1996

Résumé

A neural network is a computational network composed of mathematically defined elements that are thought to approximate the workings of biological neurons. In situations where a decision depends on many factors, neural networks provided decisions with more consistency and accuracy than trained a human. Networks are based on substantial theoretical foundations and have great practical utility in many situations. Any problem that has traditionally been solved using statistical methods or through traditional modeling can most likely be more effectively solved using neural networks. The field of neural networks has developed to the point where the underlying code can be formalized, realized as objects, and used in countless applications. Therefore, the powerful concepts of object-oriented design and object-oriented programming can now be implemented fully in creating neural network architectures. Instead of focusing on the mechanics of the underlying foundation, neural network objects allow the designer to focus upon the enhancement of an existing architecture or the design of a new one. This book is the first to take full advantage of the reusable nature of classes in neural network design.

Object-Oriented Neural Networks in C++ is a valuable tool for anyone who wants to understand, implement, or utilize neural networks. This book/disk package provides the reader with a foundation from which any neural network architecture can be constructed. The author has employed object-oriented design and object-oriented programming concepts to develop a set of foundation neural network classes, and shows how these classes can be used to implement a variety of neural network architectures with a great deal of ease and flexibility. A wealth of neural network formulas (with standardized notation), object code implementations, and examples are provided to demonstrate the object-oriented approach to neural network architectures and to facilitate the development of new neural network architectures. This is the first book to take full advantage of the reusable nature of neural network classes.

KEY FEATURES

  • Describes how to use the classes provided to implement a variety of neural network architectures including ADALINE, Backpropagation, Self-Organizing, and BAM
  • Provides a set of reusable neural network classes, created in C++, capable of implementing any neural network architecture
  • Includes an IBM disk of the source code for the classes, which is platform independent

Table of contents

Preface.Introduction: Biological Roots.

Types of Neural Networks.
Software Engineering and Object-Oriented Programming.
Other Attempts to Construct Object-Oriented Neural Networks.
Overview of the Remaining Chapters.
Object-Orientd Programming Review: Objects and Classes.
Inheritance.
Virtual Functions.
Polymorphism and Dynamic Binding.
Template Classes.
Neural-Network Base Classes: Mathematical Foundation.
Pattern Set Formalization.
Formalized Neural-Network Parameters.
ADALINE Network: Formalizing the ADALINE.
Realizing the ADALINE Neural Network Objects.
ADALINE_Link Class.
ADALINE Training Set.
Creating the ADALINE Network.
Training the ADALINE Network.
ADALINE_Network Class.
ADALINE Neural-Network Objects Summary.
Backpropagation Neural Network: Formalizing the Backpropagation Neural Network.
Realizing the Backpropagation Neural Network Objects.
Using the Backpropagation Neural-Network Objects.
Backpropagation Neural Network Node.
Backprop Application.
Epoch Training with Backpropagation Neural Networks.
Generic Backpropagation Neural Network Class.
Backpropagation Neural Network Examples.
Summary of Backpropagation Neural-Network Objects.
Self-Organizing Neural Network: Self-Organizing Neural-Network Formalism.
Realizing the Self-Organizing Neural-Network Objects.
Using the SON Objects.
SON_Network Class.
SON Application.
SON Examples.
Summary on SON Objects.
Bidirectional Associative Memory: Formalizing the BAM.
Realizing the BAM Objects.
Using the BAM Objects.
BAM Network Node.
BAM System.
BAM Objects Summary.
Appendixes.
Subject Index.

Caractéristiques techniques

  PAPIER
Éditeur(s) Apress
Auteur(s) Joey Rogers
Parution 10/10/1996
Nb. de pages 310
EAN13 9780125931151
ISBN13 978-0-12-593115-1

Avantages Eyrolles.com

Livraison à partir de 0,01 en France métropolitaine
Paiement en ligne SÉCURISÉ
Livraison dans le monde
Retour sous 15 jours
+ d'un million et demi de livres disponibles
satisfait ou remboursé
Satisfait ou remboursé
Paiement sécurisé
modes de paiement
Paiement à l'expédition
partout dans le monde
Livraison partout dans le monde
Service clients sav@commande.eyrolles.com
librairie française
Librairie française depuis 1925
Recevez nos newsletters
Vous serez régulièrement informé(e) de toutes nos actualités.
Inscription