Skip to main content
. 2006 Sep 22;2(9):e131. doi: 10.1371/journal.pcbi.0020131

Figure 10. Training FB5–HMM.

Figure 10

(Left) ICL plotted versus hidden node size. For each hidden node size, four models were trained. The ICL reaches a maximum for one of the models with a hidden node size of 75 (indicated with a solid dot).

(Right) Evolution of the LogLik of the completed data during training. The LogLik is plotted against the number of EM iterations.