6. To initialize the EM algorithm in Figure 10.6 consider two alternatives:

(a) allow P to return a random distribution the first time through the loop

(b) initialize cc and fc to random values By running the algorithm on some data sets, determine which, if any, of these alternatives is better in terms of log loss of the training data, as a function of the number of loops through the data set. Does it matter if cc and fc are not consistent with the semantics (counts that should be equal are not)?