Timezone: »

 
Poster
FlowHMM: Flow-based continuous hidden Markov models
Pawel Lorek · Rafal Nowak · Tomasz Trzcinski · Maciej Zieba

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #115

Continuous hidden Markov models (HMMs) assume that observations are generated from a mixture of Gaussian densities, limiting their ability to model more complex distributions. In this work, we address this shortcoming and propose novel continuous HMM models, dubbed FlowHMMs, that enable learning general continuous observation densities without constraining them to follow a Gaussian distribution or their mixtures. To that end, we leverage deep flow-based architectures that model complex, non-Gaussian functions and propose two variants of training a FlowHMM model. The first one, based on gradient-based technique, can be applied directly to continuous multidimensional data, yet its application to larger data sequences remains computationally expensive. Therefore, we also present a second approach to training our FlowHMM that relies on the co-occurrence matrix of discretized observations and considers the joint distribution of pairs of co-observed values, hence rendering the training time independent of the training sequence length. As a result, we obtain a model that can be flexibly adapted to the characteristics and dimensionality of the data. We perform a variety of experiments in which we compare both training strategies with a baseline of Gaussian mixture models. We show, that in terms of quality of the recovered probability distribution, accuracy of prediction of hidden states, and likelihood of unseen data, our approach outperforms the standard Gaussian methods.

Author Information

Pawel Lorek (University of Wrocław, Tooploox)
Rafal Nowak (Univeristy of Wroclaw, Tooploox)
Tomasz Trzcinski (Warsaw University of Technology, Tooploox, IDEAS, Jagiellonian University)
Maciej Zieba (Tooploox, Wroclaw University of Science and Technology)

More from the Same Authors