this is for holding javascript data
Lucas Fidon edited subsection_Visualization_of_result_Once__.tex
almost 8 years ago
Commit id: 85c99d33cecd8c0e027a667c456d5cf9e1ea6146
deletions | additions
diff --git a/subsection_Visualization_of_result_Once__.tex b/subsection_Visualization_of_result_Once__.tex
index 1f011b4..fee7bf5 100644
--- a/subsection_Visualization_of_result_Once__.tex
+++ b/subsection_Visualization_of_result_Once__.tex
...
Once probability distributions and joint distributions are estimated, the MI-based distance between all couple of trajectories $d_{MI}(T_{i},T_{j})$ can be calculated using the forms $(7)$ and $(8)$, gathered in a distance matrix.
\[M = \left( \begin{array}{ccc}
d_{MI}(T_{1},T_{1}) & \cdots & d_{MI}(T_{1},T_{n}) \\
\vdots &
\ddots & \vdots \\
d_{MI}(T_{1},T_{n}) & \cdots & d_{MI}(T_{n},T_{n}) \end{array} \right).\]
And then the clustering of the whole set of trajectories can be calculated using the clustering algorithm of \cite{NIPS2008_3478}.