úÎ@ "The type of Hidden Markov Models.  0Perform a single step in the Viterbi algorithm. PTakes a list of path probabilities, and an observation, and returns the updated 1 list of (surviving) paths with probabilities. ,The initial value for the Viterbi algorithm /Perform a single step of the forward algorithm JEach item in the input and output list is the probability that the system " ended in the respective state. ,The initial value for the forward algorithm ?Calculate the parameters of an HMM from a list of observations ! and the corresponding states.  Test Viterbi'8s algorithm on an HMM by comparing the predicted states . against known states for the observations. RCalculate the most likely sequence of states for a given sequence of observations  using Viterbi' s algorithm >Calculate the probability of a given sequence of observations ! using the forward algorithm.      hmm-0.1Data.HMM Data.LognumHMMProbtrain bestSequence sequenceProbLognumL fromFloating toFloatinglogify2viterbi viterbi_initforward forward_init learn_stateslearn_transitionslearn_observations histogram readBrownFile testViterbitrain2