\begin{enumerate}
\item Pre-processing
\begin{itemize}
- \item Input data formating (1D~vector; sampling period $\rightarrow \delta \tau$)
+ \item Input data formatting (1D~vector; sampling period $\rightarrow \delta \tau$)
\item $W^I$ initialization (randomly; normalization)
\end{itemize}
\item Concatenation of 1D~vectors $\rightarrow$ batch processing
\item Different regression tests are also independent
\end{itemize}
\end{femtoBlock}
- \smallskip
+\end{frame}
+
+\begin{frame}{Parallelization Scheme} % Slide 9
\begin{femtoBlock}
{In practice\\}
\begin{itemize}
\item Simulation code rewritten in C++
- \item {\bf M}essage~{\bf P}assing~{\bf I}nterface~for~InterProcess~Communication
+ \item Eigen C++ library for linear algebra operations
+ \item InterProcess~Communication \\
+ $\rightarrow$ {\bf M}essage~{\bf P}assing~{\bf I}nterface
\end{itemize}
\end{femtoBlock}
\smallskip
\begin{femtoBlock}
- {Test of new idea?\\}
+ {Performance on speech recognition problem\\}
+ \begin{itemize}
+ \item Same WER $\rightarrow$ similar classification accuracy
+ \item Reduced computation time
+ \end{itemize}
+ \centering
+ \vspace{0.125cm}
+ {\bf We can study problems with huge Matlab computation time}
+ \end{femtoBlock}
+ \medskip
+ \begin{femtoBlock}
+ {Testing a new idea?\\}
\vspace{0.25cm}
\centering
First test with Matlab and then adapt to C++ with MPI
\end{femtoBlock}
\end{frame}
-\begin{frame}{Finding Optimal Parameters} % Slide 9
+\begin{frame}{Finding Optimal Parameters} % Slide 10
% 1 - Quels parametres et pourquoi ?
\begin{femtoBlock}
{What parameters can be optimized?\\}
\item Next
\begin{itemize}
\item Number of nodes significantly improving the solution (threshold)
- \item Input data filter (convolutional filter for images)
+ \item Input data filter (convolution filter for images)
\end{itemize}
\end{itemize}
\centering
\begin{itemize}
\item Currently $\rightarrow$ simulated annealing \\
{\small (probabilistic global search controlled by a cooling schedule)}
- \item Next $\rightarrow$ other metaheuristics like evolutionay algorithms
+ \item Next $\rightarrow$ other metaheuristics like evolutionary algorithms
\end{itemize}
\end{femtoBlock}
\end{frame}
-\begin{frame}{Performances of the parallel code} % Slide 10
+\section{Performances on the MNIST problem}
+
+\begin{frame}{Application on the MNIST problem} % Slide 11
\begin{femtoBlock}
- {Speech recognition problem\\}
+ {Task of handwritten digits recognition\\}
+ \centering
+ \vspace{0.125cm}
+ National Institute of Standards and Technology database
\begin{itemize}
- \item Same WER $\rightarrow$ similar classification accuracy
- \item Reduced computation time $\rightarrow$ speedup...
+ \item Training dataset $\rightarrow$ american census bureau employees
+ \item Test dataset $\rightarrow$ american high school students
\end{itemize}
+ \end{femtoBlock}
+ \smallskip
+ \begin{femtoBlock}
+ {Mixed-NIST database is widely used in machine learning\\}
\centering
- \vspace{0.25cm}
- We can study problems with huge Matlab computation time
+ \vspace{0.125cm}
+ Mixing of both datasets and improved images
+ \begin{columns}
+ \begin{column}{7.5cm}
+ \begin{itemize}
+ \item Datasets
+ \begin{itemize}
+ \item Training $\rightarrow$ 60,000 samples
+ \item Test $\rightarrow$ 10,000 samples
+ \end{itemize}
+ \item Grayscale Images
+ \begin{itemize}
+ \item Normalized to fit into a $20\times20$ pixel bounding box
+ \item Centered and anti-aliased
+ \end{itemize}
+ \end{itemize}
+ \end{column}
+ \begin{column}{3cm}
+ \centering
+ \includegraphics[width=3cm]{mnist.png}
+ \end{column}
+ \end{columns}
\end{femtoBlock}
+ % 1 - Decrire ce qu'est le MNIST
+ % 2 - Setup de notre reservoir
\end{frame}
-\section{Performances on the MNIST problem}
+\begin{frame}{Performances of the parallel code} % Slide 12
+ % To be completed
+ 10000 images:\\
+ 1000 reservoirs of 2 neurons, error : 3.85\%\\
+ 1 reservoir of 2000 neurons, error : 7.14\%
+ \includegraphics[width=7.5cm]{speedup.pdf}
+\end{frame}
-\begin{frame}{Application on the MNIST problem} % Slide 12
- % 1 - Decrire ce qu'est le MNIST
- % 2 - Setup de notre reservoir
+\begin{frame}{Exploring ways to improve the results} % Slide 13
+ % Tableau recapitulant les performances
\end{frame}
-\begin{frame}{Comparison with other approaches} % Slide 13
+\begin{frame}{Comparison with other approaches} % Slide 14
% 1 - Convolutional Neural Networks
% 2 - Reservoir en pipeline (papier de 2015)
\end{frame}
-\begin{frame}{Comparison with other approaches} % Slide 14
+\begin{frame}{Comparison with other approaches} % Slide 15
% Tableau recapitulant les performances
\end{frame}
\section{Conclusion and perspectives}
-\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
-
+\begin{frame}{Conclusion and perspectives} % Slide 16
+ \begin{femtoBlock}
+ {Results\\}
+ \begin{itemize}
+ \item A parallel code allowing fast simulations
+ \item An evaluation on the MNIST problem
+ \end{itemize}
+ \end{femtoBlock}
+ \begin{femtoBlock}
+ {Future works\\}
+ \begin{itemize}
+ \item Further code improvement
+ \item Use of several reservoirs
+ \begin{itemize}
+ \item Committees
+ \item Correct errors of a reservoir by another one
+ \end{itemize}
+ \end{itemize}
+ \end{femtoBlock}
+ %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}
