A Preconditioned Unconstrained Optimization Method for Training Multilayer Feed-forward Neural Network

Non-linear unconstrained optimization  methods constitute excellent neural network training methods characterized by their simplicity and efficiency. In this paper, we propose a new preconditioned conjugate gradient neural network training algorithm which guarantees descent property with standard Wo...

Full description

Bibliographic Details
Main Authors: Khalil ABBO, Zahra ZAHRA ABDLKAREEM
Format: Article
Language:English
Published: Journal of Multidisciplinary Modeling and Optimization 2020-02-01
Series:Journal of Multidisciplinary Modeling and Optimization
Subjects:
Online Access:https://dergipark.org.tr/tr/pub/jmmo/issue/52642/496993?publisher=http-w3-sdu-edu-tr-personel-00606-prof-dr-ahmet-sahiner