Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Hidden Markov Models

Hidden Markov Models (HMMS) are the next logical step from learning about Markov Decision Processes (MDPs). They are a special case of problem for sequential reasoning.

What do we mean by sequential? These are problems where the states of the world move from state to state in a single chain without branching. This is most relevant to reasoning over time sequences, such as in speech recognition (identifying the sounds in a wave form) or robot movement (positions over time).

The lecture videos for this short unit explain how to model with probability distributions the likelihood of a particular state’s value given observations in the world.

SI420 Artificial Intelligence
Reinforcement Learning
SI420 Artificial Intelligence
Bayesian Belief Networks