deletions | additions       diff --git a/section_Clustering_with_Mutual_Information__.tex b/section_Clustering_with_Mutual_Information__.tex  index acf38e5..c45882b 100644  --- a/section_Clustering_with_Mutual_Information__.tex  +++ b/section_Clustering_with_Mutual_Information__.tex 
...
\section{Clustering with Mutual Information based metric}  \subsection{Clustering via LP-based stabilities}  Clustering is considered as one of the most fundamental unsupervised learning methods.We used the clustering algorithm described in \cite{NIPS2008_3478}. It is based on the introduced notion of stabilities of the data points to cluster. The stability of a data point measure how much we need to penalize that point such that it can no longer be chosen as a center in an optimal solution of the problem. Thanks to a measure of this stability this algorithm managed to cluster data points based on an arbitrary matrix of distances, which is the single input required by the algorithm. This quality is essential for our case since it allows us to built a relevant metric for trajectories linked to the dependencies of the distribution of players' position throw the time.  \subsection{Metrics for trajectories}  \subsection{Longuest Common Subsequence (LCSS)}  \subsection{Mutual Information based metric}  \subsubsection{Mutual Information: definition and properties}  \subsubsection{MI-based metric for trajectories}  \subsubsection{Empirical MI-based metric for trajectories}