deletions | additions       diff --git a/exp_2.tex b/exp_2.tex  index 0805988..bbaca59 100644  --- a/exp_2.tex  +++ b/exp_2.tex 
...
Table \ref{table:seg_values} contains the average, maximum and minimum values obtained for the F1 measure\cite{fawcett2006introduction} of the character segmentation problem. The F1 measure is used instead of the accuracy because the two classes are imbalanced: there are 11475 data points which indicate a segmentation point, while there are 19402 points which are not segmentation points, almost twice as many.   \begin{table}[h]  \caption{The F1 score for the character segmentation experiment}  \label{table:seg_values}  \begin{tabular}{llllll}  \hline  Number of trees & Number of features & Min & Max & Mean & Std. dev. \\ \hline  150 & 20 & 0.87318 & 0.88326 & 0.87735 & 0.00363 \\   200 & 20 & 0.86975 & 0.88312 & 0.87657 & 0.00490 \\   250 & 20 & 0.87258 & 0.88776 & 0.87773 & 0.00531 \\   150 & 8 & 0.86894 & 0.88376 & 0.87569 & 0.00517 \\   200 & 8 & 0.87227 & 0.88299 & 0.87675 & 0.00413 \\   250 & 8 & 0.87178 & 0.88470 & 0.87717 & 0.00426 \\   150 & 120 & 0.87262 & 0.88631 & 0.87816 & 0.00476 \\   200 & 120 & 0.87122 & 0.88387 & 0.87724 & 0.00418 \\   250 & 120 & 0.87367 & 0.88565 & 0.87885 & 0.00391 \\   150 & 40 & 0.87073 & 0.88671 & 0.87822 & 0.00552 \\   200 & 40 & 0.86980 & 0.88519 & 0.87845 & 0.00513 \\   250 & 40 & 0.87358 & 0.88671 & 0.87936 & 0.00445 \\ \hline  \end{tabular}  \end{table}  Table \ref{table:seg_conf} contains the confusion matrix for the best experiment on the character segmentation problem.  \begin{table}[h]