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

Home Page
About
Submit A Journal
Submit A Conference
Submit Paper/Book
- Submit a Preprint
- Submit a Book
Contact

Journal of Multidisciplinary Modeling and Optimization
Volume:2 Issue:2
A Preconditioned Unconstrained Optimization Method for Training Multilayer Feed-forward Neural Netwo...

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

Authors : Khalil ABBO, Zahra ZAHRA ABDLKAREEM

Pages : 71-79

View : 24 | Download : 2

Publication Date : 2020-02-24

Article Type : Research Paper

Abstract :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 Wolfe condition. Encouraging numerical experiments verify that the proposed algorithm provides fast and stable convergence.
Keywords : Unconstrained optimization, Neural network, Descent property

ORIGINAL ARTICLE URL

* There may have been changes in the journal, article,conference, book, preprint etc. informations. Therefore, it would be appropriate to follow the information on the official page of the source. The information here is shared for informational purposes. IAD is not responsible for incorrect or missing information.

Index of Academic Documents
İzmir Academy Association
CopyRight © 2023-2026