Incremental Estimation of Discrete Hidden Markov Models Based on a New Backward Procedure

Book One

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 20

Machine Learning

We address the problem of learning discrete hidden Markov models from very long sequences of observations. Incremental versions of the Baum-Welch algorithm that approximate the β-values used in the backward procedure are commonly used for this problem, since their memory complexity is independent of the sequence length. We introduce an improved incremental Baum-Welch algorithm with a new backward procedure that pproximates the β-values based on a one-step lookahead in the training sequence. We justify the new approach analytically, and report empirical results that show it converges faster than previous incremental algorithms.