Rolfe, Jason T. and Cook, Matthew (2010) Multifactor Expectation Maximization for Factor Graphs. In: Artificial Neural Networks - ICANN 2010, Part III. Lecture Notes in Computer Science (6354). Springer , Berlin, pp. 267-276. ISBN 978-3-642-15824-7 http://resolver.caltech.edu/CaltechAUTHORS:20110524-092936998
Full text not available from this repository.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20110524-092936998
Factor graphs allow large probability distributions to be stored efficiently and facilitate fast computation of marginal probabilities, but the difficulty of training them has limited their use. Given a large set of data points, the training process should yield factors for which the observed data has a high likelihood. We present a factor graph learning algorithm which on each iteration merges adjacent factors, performs expectation maximization on the resulting modified factor graph, and then splits the joined factors using non-negative matrix factorization. We show that this multifactor expectation maximization algorithm converges to the global maximum of the likelihood for difficult learning problems much faster and more reliably than traditional expectation maximization.
|Item Type:||Book Section|
|Additional Information:||© 2010 Springer-Verlag Berlin Heidelberg.|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||03 Jun 2011 21:36|
|Last Modified:||03 Jun 2011 21:36|
Repository Staff Only: item control page