On Neural Network Algorithms for Solving Non- Linear Problems: Optimizations and Non-linear programming - Brossura

Sadq, Gulnar; Younis Al-Bayati, Abbas; Abdulla Sulaiman, Najmaddin

Brossura

ISBN 10: 3846580805 ISBN 13: 9783846580806

Casa editrice: LAP LAMBERT Academic Publishing, 2012

Riassunto

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.

Su questo libro

L'autore

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.

Dettagli dell?edizione

• Editore: LAP LAMBERT Academic Publishing
• Data di pubblicazione: 2012
• Lingua: Inglese
• ISBN 10: 3846580805
• ISBN 13: 9783846580806
• Rilegatura: Copertina flessibile
• Numero di pagine: 156
• Contatto del produttore: non disponibile