CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2009 vol.31 Issue No.02 - February
Issue No.02 - February (2009 vol.31)
Shihao Ji , Duke University, Durham
Layne T. Watson , Virginia Polytechnic Institute and State Univeristy, Blacksburg
Lawrence Carin , Duke University, Durham
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2008.71
Hidden Markov model (HMM) classifier design is considered for the analysis of sequential data, incorporating both labeled and unlabeled data for training; the balance between the use of labeled and unlabeled data is controlled by an allocation parameter \lambda \in [0, 1), where \lambda = 0 corresponds to purely supervised HMM learning (based only on the labeled data) and \lambda = 1 corresponds to unsupervised HMM-based clustering (based only on the unlabeled data). The associated estimation problem can typically be reduced to solving a set of fixed-point equations in the form of a ?natural-parameter homotopy.
Semisupervised learning, homotopy method, hidden Markov models (HMMs), supervised learning.
Shihao Ji, Layne T. Watson, Lawrence Carin, "Semisupervised Learning of Hidden Markov Models via a Homotopy Method", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.31, no. 2, pp. 275-287, February 2009, doi:10.1109/TPAMI.2008.71