A computational study on the performance of artificial neural networks under changing structural design and data distribution

A computational study on the performance of artificial neural networks under changing structural design and data distribution

0.00 Avg rating0 Votes
Article ID: iaor20023361
Country: Netherlands
Volume: 138
Issue: 1
Start Page Number: 155
End Page Number: 177
Publication Date: Apr 2002
Journal: European Journal of Operational Research
Authors:
Keywords: statistics: data envelopment analysis
Abstract:

This paper provides the results of our computational studies on artificial neural networks (ANNs) under various structural design and data distributions. A two-group classification problem is investigated. Simulated data with varying kurtosis and variance are used to examine how the ANN performs with respect to certain structural design (size and addition of input and weight noise) characteristics. The results of our study indicate that additive noise, size, and data distribution characteristics play an important role in learning, reliability and predictive ability of ANNs.

Reviews

Required fields are marked *. Your email address will not be published.