Figure 17From: XRate: a fast prototyping, training and annotation tool for phylo-grammarsLog-likelihoods (log2 P(alignment, annotation|parameters), red line) increase as the EM algorithm optimizes the model parameters on the training set. The accuracy results for this parameterization are reported in Table 4. The blue line represents the asymptotic best log-likelihood, reached at iteration 27.Back to article page