Assessment of an Unsupervised Feature Selection Method for Generative Topographic Mapping
Feature selection (FS) has long been studied in classification and regression problems. In comparison, FS for unsupervised learning has received far less attention. For many real problems concerning unsupervised data clustering, FS becomes an issue of paramount importance. An unsupervised FS method for Gaussian Mixture Models, based on Feature Relevance Determination (FRD), was recently defined. Unfortunately, the data visualization capabilities of general mixture models are limited. Generative Topographic Mapping (GTM), a constrained mixture model, was originally defined to overcome such limitation. In this brief study, we test in some detail the capabilities of a recently described FRD method for GTM that allows the clustering results to be intuitively visualized and interpreted in terms of a reduced subset of selected relevant features.
KeywordsFeature Selection Mixture Model Gaussian Mixture Model Finite Mixture Model Adaptive Parameter
Unable to display preview. Download preview PDF.
- 4.Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer, Berlin (2000)Google Scholar
- 8.MacKay, D.J.C.: Bayesian Methods for Back-Propagation Networks. In: Domany, E., van Hemmen, J.L., Schulten, K. (eds.) Models of Neural Networks III, pp. 211–254. Springer, New York (1994)Google Scholar
- 9.Andrade, A., Vellido, A.: Determining Feature Relevance for the Grouping of Motor Unit Action Potentials through Generative Topographic Mapping. In: Proc. of the 25th IASTED International Conference Modelling, Identification, and Control (MIC 2006), pp. 507–512 (2006)Google Scholar
- 11.Dash, M., Liu, H., Yao, J.: Dimensionality Reduction for Unsupervised Data. In: Proc. Of the 9th Int. Conf. on Tools with Artificial Intelligence (TAI 1997), pp. 532–539 (1997)Google Scholar