What are the mathematics that are necessary to understand Hidden Markov Models? Matrix Algebra? Linear algebra? Calculus? Bayesian statistcs?
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
3
Basic probability theory (i.e. when to sum versus multiply probabilities) is the only essential requirement. For Bayesian HMMs you would of course need to understand Bayesian inference, but HMMs do not have to be Bayesian. People get intimidated by Hidden Markov Models but they're actually quite easy to understand if you work through a few examples.
-
1$\begingroup$ I do agree. However in most textbooks, basic linear algebra will be used. If you want to be prepared to Baum Welsch, have a look on EM algorithm. $\endgroup$– ElvisCommented Dec 7, 2012 at 22:35
-
$\begingroup$ What does "to Baum Welsch" mean? What is EM algorithm? $\endgroup$ Commented Dec 8, 2012 at 0:28
-
$\begingroup$ @AronLindberg, Baum Welch is a standard algorithm for learning the parameters of the HMM. You can find plenty more information on it by doing a google search. $\endgroup$– jeradCommented Dec 9, 2012 at 20:28