Title :
Mode-finding for mixtures of Gaussian distributions
Author :
Carreira-Perpiñán, Miguel AÁ
Author_Institution :
Dept. of Neurosci., Georgetown Univ. Med. Center, Washington, DC, USA
fDate :
11/1/2000 12:00:00 AM
Abstract :
Gradient-quadratic and fixed-point iteration algorithms and appropriate values for their control parameters are derived for finding all modes of a Gaussian mixture, a problem with applications in clustering and regression. The significance of the modes found is quantified locally by Hessian-based error bars and globally by the entropy as sparseness measure.
Keywords :
Gaussian distribution; covariance analysis; entropy; search problems; Hessian-based error bars; clustering; fixed-point iteration algorithms; gradient-quadratic algorithms; mixtures of Gaussian distributions; mode-finding; regression; sparseness measure; Algorithm design and analysis; Bars; Bayesian methods; Clustering algorithms; Covariance matrix; Entropy; Gaussian distribution; Hidden Markov models; Machine learning algorithms; Speech analysis;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
