Stepwise Linear Regression Dimensionality Reduction in Neural Network Modelling

Addison, Jonathan, McGarry, Kenneth, Wermter, Stefan and MacIntyre, John (2004) Stepwise Linear Regression Dimensionality Reduction in Neural Network Modelling. In: Proceedings of the International Conference on Artificial Intelligence and Applications, 16-18 February 2004, Innsbruck, Austria.

Full text not available from this repository. (Request a copy)

Abstract

This work considers the applicability of applying the derivatives of stepwise linear regression modelling (specifically the p-values which indicate the importance of a variable to the modelling process) as a feature extraction technique. We utilise it in conjunction with several data sets of varying levels of complexity, and compare our results to other dimensionality reduction techniques such as genetic algorithms, sensitivity analysis and linear principal components analysis prior to data modelling using several different neural network models. Our results indicate that stepwise linear regression is highly effective in this role with results comparable to and sometimes superior then more established techniques

Item Type: Conference or Workshop Item (Paper)
Subjects: Computing > Artificial Intelligence
Computing > Information Systems
Divisions: Faculty of Applied Sciences
Depositing User: Kenneth McGarry
Date Deposited: 11 Mar 2015 11:44
Last Modified: 11 Mar 2015 11:44
URI: http://sure.sunderland.ac.uk/id/eprint/5281

Actions (login required)

View Item View Item