Skip header navigation
×

Conference Proceeding

A walsh analysis of multilayer perceptron function

Citation
Swingler K (2014) A walsh analysis of multilayer perceptron function. In: Proceedings of the International Conference on Neural Computation Theory and Applications (IJCCI 2014). NCTA 2014: 6th International Conference on Neural Computation Theory and Applications, Rome, Italy, 22.10.2014-24.10.2014. Setubal, Portugal: Science and Technology Publications, pp. 5-14. http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0004974800050014; https://doi.org/10.5220/0004974800050014

Abstract
The multilayer perceptron (MLP) is a widely used neural network architecture, but it suffers from the fact that its knowledge representation is not readily interpreted. Hidden neurons take the role of feature detectors, but the popular learning algorithms (back propagation of error, for example) coupled with random starting weights mean that the function implemented by a trained MLP can be difficult to analyse. This paper proposes a method for understanding the structure of the function learned by MLPs that model functions of the class f : f1;1gn ! Rm. The approach characterises a given MLP using Walsh functions, which make the interactions among subsets of variables explicit. Demonstrations of this analysis used to monitor complexity during learning, understand function structure and measure the generalisation ability of trained networks are presented.

Keywords
Multilayer Perceptrons; Walsh Functions; Network Function Analysis

StatusPublished
Author(s)Swingler, Kevin
Publication date31/12/2014
Related URLshttp://www.ncta.ijcci.org/?y=2014
PublisherScience and Technology Publications
Publisher URLhttp://www.scitepress.org/…0004974800050014
Place of publicationSetubal, Portugal
ISBN978-989-758-054-3
ConferenceNCTA 2014: 6th International Conference on Neural Computation Theory and Applications
Conference locationRome, Italy
Dates
Scroll back to the top