PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

PAC-learning of Markov models with hidden state
Ricard Gavaldà, Philipp W. Keller, Joelle Pineau and Doina Precup
In: 17th European Conference on Machine Learning (ECML'06), 18-22 Sep 2006, Berlin, Germany.

Abstract

The standard approach for learning Markov Models with Hidden State uses the Expectation-Maximization framework. While this approach had a significant impact on several practical applications (e.g. speech recognition, biological sequence alignment) it has two major limitations: it requires a known model topology, and learning is only locally optimal. We propose a new PAC framework for learning both the topology and the parameters in partially observable Markov models. Our algorithm learns a Probabilistic Deterministic Finite Automata (PDFA) which approximates a Hidden Markov Model (HMM) up to some desired degree of accuracy. We discuss theoretical conditions under which the algorithm produces an optimal solution (in the PAC-sense) and demonstrate promising performance on simple dynamical systems.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Additional Information:Also available for browsing from the author's homepage, subject to the copyright restrictions.
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:2933
Deposited By:Ricard Gavaldà
Deposited On:23 November 2006