Factorial Hidden Markov Models.

Abstract

Abstract. Hidden Markov models (HMMs) have proven to be one of the most widely used tools for learning probabilistic models of time series data. In an HMM, information about the past is conveyed through a single discrete variable-the hidden state. We discuss a generalization of HMMs in which this state is factored into multiple state variables and is therefore represented in a distributed manner. We describe an exact algorithm for inferring the posterior probabilities of the hidden state variables given the observations, and relate it to the forward-backward algorithm for HMMs and to algorithms for more general graphical models. Due to the combinatorial nature of the hidden state representation, this exact algorithm is intractable. As in other intractable systems, approximate inference can be carried out using Gibbs sampling or variational methods. Within the variational framework, we present a structured approximation in which the the state variables are decoupled, yielding a tractable algorithm for learning the parameters of the model. Empirical comparisons suggest that these approximations are efficient and provide accurate alternatives to the exact methods. Finally, we use the structured approximation to model Bach's chorales and show that factorial HMMs can capture statistical structure in this data set which an unconstrained HMM cannot.

Automating the Calibration of a Neonatal Condition Monitoring System

“…Switching [3,8,13] and factorization [4] are two well-known ideas for relaxing the assumptions made by state-space models on the probability distribution of the data. The FSLDS [10,12,15] combines both with the advantages of autoregressive (AR) processes to model baby monitoring.…”

Modelling Patterns of Evidence in Bayesian Networks: A Case-Study in Classical Swine Fever

“…We would like to note that modelling the relevant patterns of evidence in our CSF network by introducing phase variables and their transitional relations bears a strong resemblance to the modelling of stochastic processes in hidden Markov models and their extensions [7,8]. A major difference between our approach and these types of model, however, is that the arcs between our phase variables are not associated with a time interval; also the transition probabilities describing the relationships between the phases do not involve any reference to time.…”

Robust Visual Tracking by Integrating Multiple Cues Based on Co-Inference Learning

“…The optimal model parameters as well as the variational parameters would be found by minimizing the discrepancy between these two distributions. A lower bound on the log likelihood log P (Z t ) can be achieved by such an approximation (Saul and Jordan, 1996;Ghahramani, 1995;Ghahramani and Jordan, 1997;Jordan et al, 2000):…”