Andere Kunden interessierten sich auch für
![Universal method for solving problems of linear algebra]( "Universal method for solving problems of linear algebra")
Universal method for solving problems of linear algebra32,99 €![Solving Problems in Science and Engineering By Matrix Method]( "Solving Problems in Science and Engineering By Matrix Method")
Solving Problems in Science and Engineering By Matrix Method29,99 €![Boundary Value Problems in Linear Transport]( "Boundary Value Problems in Linear Transport")
Boundary Value Problems in Linear Transport24,99 €![Boundary value problems for some quasi-linear parabolic equations]( "Boundary value problems for some quasi-linear parabolic equations")
Boundary value problems for some quasi-linear parabolic equations20,99 €![Design feed forward neural networks for solving ordinary intial value]( "Design feed forward neural networks for solving ordinary intial value")
Design feed forward neural networks for solving ordinary intial value40,99 €![Modified nonlinear CG algorithms with application in Neural Networks]( "Modified nonlinear CG algorithms with application in Neural Networks")
Modified nonlinear CG algorithms with application in Neural Networks40,99 €![Techniques for solving programming problems]( "Techniques for solving programming problems")
Techniques for solving programming problems32,99 €
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.