single-jc.php

JACIII Vol.5 No.1 pp. 31-36
doi: 10.20965/jaciii.2001.p0031
(2001)

Paper:

An Innovative Way to Measure the Quality of a Neural Network Without the Use of a Test Set

Giovanni Pilato*, Filippo Sorbello* and Giorgio Vassallo**

Department of Automata and Informatics Engineering University of Palermo Viale delle Scienze, Palermo, Italy CRES Centro per la Ricerca Elettronica in Sicilia Via Regione Siciliana, Monreale (PA), Italy

Received:
October 20, 2000
Accepted:
December 10, 2000
Published:
January 20, 2001
Keywords:
Neural networks, Quality factors, Generalization capability
Abstract

In this paper, three quality factors are introduced in order to measure the quality of a neural network. Each factor deals with a particular feature of quality: the ability of the network in learning training set samples; generalization capability related to the gradient, in the nearby of the training patterns, of the network output function; the computational cost of the architecture during the production phase, related to the number of connections between neural units. The validity of the proposed solution has been tested using three well-known benchmarks. Experimental results show that quality factors introduced in this paper can be a valid alternative to the test set method.

Cite this article as:
Giovanni Pilato, Filippo Sorbello, and Giorgio Vassallo, “An Innovative Way to Measure the Quality of a Neural Network Without the Use of a Test Set,” J. Adv. Comput. Intell. Intell. Inform., Vol.5, No.1, pp. 31-36, 2001.
Data files:

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Sep. 21, 2021