Abstract : Rejection sampling is a useful technique for performing supervised learning on training sets too large to be learned in their entirety. FilterBoost is a recent extension to AdaBoost which uses rejection sampling in an online learning framework and has been shown to work for automatic tagging of music. In this paper we improve on FilterBoost by adding Metropolis-Hastings sampling, thus allowing the algorithm to focus on hard-to-classify examples. We describe how our knowledge of artist-level similarity can be used eﬀectively in a Metropolis-Hastings framework and demonstrate a signiﬁcant increase in classiﬁcation accuracy over standard FilterBoost.
Type de document :
Communication dans un congrès
International Workshop on Machine Learning and Music (ICML08 Workshop), Jul 2008, Helsinki, Finland. 2008
Balázs Kégl, Thierry Bertin-Mahieux, Douglas Eck. Metropolis-Hastings sampling in a FilterBoost music classifier. International Workshop on Machine Learning and Music (ICML08 Workshop), Jul 2008, Helsinki, Finland. 2008. <inria-00428923>