deletions | additions       diff --git a/experiments.tex b/experiments.tex  index 2665975..2a50c20 100644  --- a/experiments.tex  +++ b/experiments.tex 
...
For the character recognition problem, the labels corresponding to each character were converted to a vector of 74 dimensions, with each dimension corresponding to one possible character value. The value of the dimension corresponding to the character of a data point was set to 1, while all the others were set to 0.   For the character segmentation problem, the labels were binary: 1 if a certain data point was were a segmentation should occur, 0 otherwise.   \begin{figure}  \centering  \begin{subfigure}{.5\textwidth}  \centering  \includegraphics[width=.4\linewidth]{figures/bon1/bon1.jpg}  \caption{A subfigure}  \label{fig:sub1}  \end{subfigure}%  \begin{subfigure}{.5\textwidth}  \centering  \includegraphics[width=.4\linewidth]{figures/1/1.jpg}  \caption{A subfigure}  \label{fig:sub2}  \end{subfigure}  \caption{A figure with two subfigures}  \label{fig:test}  \end{figure}  \subsection{Training and testing}  The data set was shuffled and then split into two parts, one for training and one for testing. The splitting was done in a random way, because the data points are independent and order does not matter. The training set contained 80\% of the data and the test set contained the remaining 20\%.