Introduction and Application of Hidden Markov Models by Jakin Miller ’24

Introduction and Application of Hidden Markov Models by Jakin Miller ’24, Wednesday April 10, 1:10 – 1:50pm, North Science Building 015, Wachenheim, Statistics Colloquium

Abstract – Markov models are commonly applied in the world of state-based stochastic processes, but things become much more complicated when the state of a process is unknown. Hidden Markov models, using the EM algorithm, allow us to use markov chains to model even when we cannot tell what state a process is in. A common application of HMMs is in earthquake prediction, as it is commonly known that earthquake activity can be grouped into high and low-activity states, but it is very difficult to determine the state of the earthquake region at a given time.