Sampling methods for unsupervised learning
Robert Fergus, Andrew Zisserman and Pietro Perona
In: NIPS 2004, 13-18 Dec 2004, Vancouver, Canada.
We present an algorithm to overcome the local maxima problem in estimating the parameters of mixture models. It combines existing approaches from both EM and a robust tting algorithm, RANSAC, to give a data-driven stochastic learning scheme. Minimal subsets of data points, suf cient to constrain the parameters of the model, are drawn from proposal densities to discover new regions of high likelihood. The proposal densities are learnt using EM and bias the sampling toward promising solutions. The algorithm is computationally ef cient, as well as effective at escaping from local maxima. We compare it with alternative methods, including EM and RANSAC, on both challenging synthetic data and the computer vision problem of alpha-matting.
|EPrint Type:||Conference or Workshop Item (Poster)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Mudigonda Pawan Kumar|
|Deposited On:||14 May 2005|