Bienvenue chez nous !
Logo Ex Libris
 Laissez-vous inspirer ! 

On Neural Network Algorithms for Solving Non- Linear Problems

  • Couverture cartonnée
  • 156 Nombre de pages
(0) Donner la première évaluation
Évaluations
(0)
(0)
(0)
(0)
(0)
Afficher toutes les évaluations
First we describe, analyze and present the theoretical derivations and the source codes for several (modified and well-known) non-... Lire la suite
CHF 80.00
Habituellement expédié sous 2 à 4 jours ouvrés.
Commande avec livraison dans une succursale

Description

First we describe, analyze and present the theoretical derivations and the source codes for several (modified and well-known) non-linear Neural Network algorithms based on the unconstrained optimization theory and applied to supervised training networks. In addition to the indication of the relative efficiency of these algorithms in an application, we analyze their main characteristics and present the MATLAB source codes. Algorithms of this part depend on some modified variable metric updates and for the purpose of comparison, we illustrate the default values specification for each algorithm, presenting a simple non-linear test problem. Further more in this thesis we also emphasized on the conjugate gradient (CG) algorithms, which are usually used for solving nonlinear test functions and are combined with the modified back propagation (BP) algorithm yielding few new fast training multilayer Neural Network algorithms. This study deals with the determination of new search directions by exploiting the information calculated by gradient descent as well as the previous search directions.

Auteur

Gulnar Wasim Sadiq, was burn in 1974 kurdistan region. Complete the PhD. Degree at University of Sulaimani- College of Science, Department of Mathematics in the field Operation Research and Optimization.

Informations sur le produit

Titre: On Neural Network Algorithms for Solving Non- Linear Problems
Auteur:
Code EAN: 9783846580806
ISBN: 978-3-8465-8080-6
Format: Couverture cartonnée
Editeur: LAP Lambert Academic Publishing
Genre: Mathématique
nombre de pages: 156
Poids: 249g
Taille: H220mm x B150mm x T9mm
Année: 2012
Auflage: Aufl.