On the quasi-Newton training method for feed-forward neural networks

Authors:
Nikolai Stanevski;Dimiter Tsvetkov
Affiliations:
Military University "Vassil Levski", Veliko Tarnovo;Cartographical Institute, Troyan
Venue:
CompSysTech '04 Proceedings of the 5th international conference on Computer systems and technologies
Year:
2004

Citing 0
Cited 2

An ordinal optimization theory-based algorithm for a class of simulation optimization problems and application

Expert Systems with Applications: An International Journal
Intelligent mobile manipulators in industrial applications: experiences and challenges

50 years of artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

The quasi-Newton training method is the most effective method for feed-forward neural networks with respect to the training precision. This method is well-known and popularly described in the neural networks literature. Nevertheless its implementation contains some difficulties because of the specific shape of the cost function and the large amount of variables. Here we give in sufficient details an example of a program implementation of the quasi-Newton method. This implementation (as a Borland Delphi application) seems to work well with various examples.