Mathematics Colloquia and Seminars

Return to Colloquia & Seminar listing

Bounds on convergence of the entropy rate block estimates for exact hidden Markov models.

Probability

Speaker: Nick Travers, UC Davis
Location: 2112 MSB
Start time: Wed, Apr 3 2013, 4:10PM

A hidden Markov model (HMM) is said to be exactly synchronizing or simply exact if there is some finite word such that an observer knows the internal state of the model with certainty after observing the output . We provide an exponential upper bound for convergence of the entropy rate block estimates in exact HMMs with finite state sets and output alphabets. We believe the bound should often be tight.