A simple way to enhance the efficiency of Nguyen-Widrow method in neural networks initialisation

Faiza Saadi and Ahmed Chibat

International Journal of Mathematics in Operational Research, 2022, vol. 21, issue 4, 497-514

Abstract: The choice of the initial values of neural network parameters is of crucial importance for the conduct and successful completion of training. The most known and most used method to perform this task is the Nguyen-Widrow method. It has brought a well-established advantage over the traditional method of purely random choice. However, this advantage is not always guaranteed. A hidden defect can appear in some situations leading to a quality deteriorate of training. In this work, the existence of this hidden defect is revealed and the way to remedy this is proposed. We show how a simple procedure, built on conditional resets, eliminates unsuitable starting conditions and ensures the steadiness of good training quality. In this way, the search for the optimal architecture of a network when processing any given problem becomes faster and more reliable.

Keywords: neural networks; weight initialisation; function approximation; regression. (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=122804 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijmore:v:21:y:2022:i:4:p:497-514

Access Statistics for this article

More articles in International Journal of Mathematics in Operational Research from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().