deletions | additions       diff --git a/methodology.tex b/methodology.tex  index e4b80c5..483126a 100644  --- a/methodology.tex  +++ b/methodology.tex 
...
This section presents the background of the machine learning approaches used in the problem of OCR and then the specifics of the models applied to this problem are discussed.   \subsection{Theoretical background}  \subsubsection{Random forests}  Random forests have been introduced by Leo Breiman and Adele Cutler\cite{breiman2001random} as an ensemble of decision trees. When using only one decision tree to make a classification, one often runs into problems with high variance or high bias. Random forests present a mechanism to avoid these problems to make more accurate models, that generalize better.   When training the random forest, for each tree, n samples are taken with replacement from the training data (a bootstrap sample)  \subsubsection{Linear SVM}  \subsection{Model design}