Inducing hidden Markov models to model long-term dependencies

Authors:
Jérôme Callut;Pierre Dupont
Affiliations:
Department of Computing Science and Engineering, INGI, Université catholique de Louvain, Louvain-la-Neuve, Belgium;Department of Computing Science and Engineering, INGI, Université catholique de Louvain, Louvain-la-Neuve, Belgium
Venue:
ECML'05 Proceedings of the 16th European conference on Machine Learning
Year:
2005

Citing 5
Cited 3

Fundamentals of speech recognition

Fundamentals of speech recognition
Bayesian learning of probabilistic language models

Bayesian learning of probabilistic language models
Planar Hidden Markov Modeling: From Speech to Optical Character Recognition

Advances in Neural Information Processing Systems 5, [NIPS Conference]
Information Extraction with HMM Structures Learned by Stochastic Optimization

Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Diffusion of context and credit information in Markovian models

Journal of Artificial Intelligence Research

Learning Partially Observable Markov Models from First Passage Times

ECML '07 Proceedings of the 18th European conference on Machine Learning
Boosting Classifiers Built from Different Subsets of Features

Fundamenta Informaticae
Sequence discrimination using phase-type distributions

ECML'06 Proceedings of the 17th European conference on Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose in this paper a novel approach to the induction of the structure of Hidden Markov Models. The induced model is seen as a lumped process of a Markov chain. It is constructed to fit the dynamics of the target machine, that is to best approximate the stationary distribution and the mean first passage times observed in the sample. The induction relies on non-linear optimization and iterative state splitting from an initial order one Markov chain.