Simultaneous Localized Feature Selection and Model Detection for Gaussian Mixtures
Yuanhong Li, Ming Dong, Jing Hua · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2008
In this paper, we propose a novel approach of simultaneous localized feature selection and model detection for unsupervised learning. In our approach, local feature saliency, together with other parameters of Gaussian mixtures, are estimated by Bayesian variational learning. Experiments performed on both synthetic and real-world data sets demonstrate that our approach is superior over both global feature selection and subspace clustering methods.