new

diff --git a/reservoir.tex b/reservoir.tex
index d3ca36800f7ab478efceb3eec0a4b3070f36a84b..022e525b8e5490367e532dfacf50b5ab9855ef04 100644 (file)
--- a/reservoir.tex
+++ b/reservoir.tex
@@ -173,26 +173,68 @@ Application on the MNIST problem}
   % Grandes lignes a partir du pdf de Laurent
   \begin{femtoBlock}
     {Main lines\\}
+    \begin{itemize}
+    \item Numerical integration to compute the nonlinear transient response
+    \item[] $\Rightarrow$ computation of matrices $A$ and $B$
+    \item Computation of the Readout
+    \item Test of the solution (cross validation)
+    \end{itemize}
   \end{femtoBlock}
   % Inconvenient de ce code => temps de calcul
   \begin{femtoBlock}
-   {Computation time\\}
+    {Computation time\\}
+    12 min for 500 words recognition (2013)
   \end{femtoBlock}
 \end{frame}
 
 \section{Parallelization and optimization}
 
 \begin{frame}{Parallelization Scheme} % Slide 8
+  \begin{itemize}
+  \item Port of the code in C++
+  \item Parallelization with MPI (Message Passing Interface)
+  \item Computation of data response (sound, image) is independent so
+    it can be parallelized
+   \item Different regression tests are also independent
+  \item Test of new idea? First test with matlab and then adapt to C++
+    with MPI
+  \end{itemize}
   % 1 - Comment le paralleliser
   % 2 - Langage et bibliotheque
 \end{frame}
 
 \begin{frame}{Finding the Optimal Parameters} % Slide 9
   % 1 - Quels parametres et pourquoi ?
+  \begin{femtoBlock}
+    {What parameters can be optimized?\\}
+    Currently:
+    \begin{itemize}
+    \item Pitch 
+    \item Delta 
+    \item Beta 
+    \item Phi
+    \item Lambda
+    \end{itemize}
+    Next:
+    \begin{itemize}
+    \item Number of nodes that significantly improve the solution (threshold)
+    \item Form of a convolutional filter?
+    \item Potentially any parameters
+    \end{itemize}
+
+  \end{femtoBlock}
 \end{frame}
 
 \begin{frame}{Finding the Optimal Parameters} % Slide 10
   % 2 - Optimisation par recuit simule
+  \begin{femtoBlock}
+    {Optimization heuristics\\}
+    \begin{itemize}
+    \item Now: Simulated annealing
+    \item[] $\Rightarrow$ probabilistic technique for approximating the global optimum of a given function.
+    \item Next: maybe other heuristics
+    \end{itemize}
+  \end{femtoBlock}
 \end{frame}
 
 \begin{frame}{Performances} % Slide 11
@@ -220,6 +262,15 @@ Application on the MNIST problem}
 
 \begin{frame}{Conclusion and perspectives} % Slide 15
 
+
+  Many perspectives (we are just beginning)
+  Improvement of the code\\
+  Test of many ideas : number of comities\\
+  One reservoir to learn and another one to learn error and correct
+  them\\
+  Test other large problems in simulation before in real\\
+  => Try to test many configuration and to find optimal parameters
+  
 \end{frame}
 
 \begin{frame}{Thank you for your attention}