Modelling neural network performance through response surface methodology for classifying wood veneer defects
Authors:
- 1 April 2004
- journal article
- research article
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture
- Vol. 218 (4) , 459-466
Abstract
This paper describes the use of response surface methodology (RSM) to model the performance of a neural network. This is in order to help select the values for the neural network parameters. The method was applied to design a multilayer perceptron network for classifying surface defects on wood veneer. The results show that the performance of the neural network was improved by this method, but extrapolation outside the tested parameter range should be avoided.Keywords
This publication has 3 references indexed in Scilit:
- Low‐cost response surface methods from simulation optimizationQuality and Reliability Engineering International, 2002
- Optimizing the parameters of multilayered feedforward neural networks through Taguchi design of experimentsQuality and Reliability Engineering International, 2000
- Neural Networks for Classifying Images of Wood Veneer. Part 2The International Journal of Advanced Manufacturing Technology, 2000