Visualization of learning in multilayer perceptron networks using principal component analysis

Gallagher, M. R. and Downs, T. (2003) Visualization of learning in multilayer perceptron networks using principal component analysis. IEEE transactions on systems, man and cybernetics. Part B, Cybernetics Part B-cybernetics, 33 1: 28-34. doi:10.1109/TSMCB.2003.808183


Author Gallagher, M. R.
Downs, T.
Title Visualization of learning in multilayer perceptron networks using principal component analysis
Journal name IEEE transactions on systems, man and cybernetics. Part B, Cybernetics Part B-cybernetics   Check publisher's open access policy
ISSN 1083-4419
Publication date 2003-01-01
Year available 2003
Sub-type Article (original research)
DOI 10.1109/TSMCB.2003.808183
Open Access Status Not Open Access
Volume 33
Issue 1
Start page 28
End page 34
Total pages 7
Editor L. Hall
Place of publication New York
Publisher The Institute of Electrical and Electronics Engineers
Language eng
Subject C1
280212 Neural Networks, Genetic Alogrithms and Fuzzy Logic
780101 Mathematical sciences
Abstract This paper is concerned with the use of scientific visualization methods for the analysis of feedforward neural networks (NNs). Inevitably, the kinds of data associated with the design and implementation of neural networks are of very high dimensionality, presenting a major challenge for visualization. A method is described using the well-known statistical technique of principal component analysis (PCA). This is found to be an effective and useful method of visualizing the learning trajectories of many learning algorithms such as back-propagation and can also be used to provide insight into the learning process and the nature of the error surface.
Keyword Automation & Control Systems
Computer Science, Artificial Intelligence
Computer Science, Cybernetics
Artificial Neural Network (ann)
Error Surface
Multilayer Perceptron
Principal Component Analysis (pca)
Visualization
Neural Networks
Q-Index Code C1
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 15 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 19 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Mon, 13 Aug 2007, 23:22:58 EST