-\JFC{revoir plan}
-
-The remainder of this research work is organized as follows. The next
-section is devoted to the basics of Devaney's chaos. Section~\ref{S2}
-formally describes how to build a neural network that operates
-chaotically. Section~\ref{S3} is devoted to the dual case of checking
-whether an existing neural network is chaotic or not. Topological
-properties of chaotic neural networks are discussed in Sect.~\ref{S4}.
-The Section~\ref{section:translation} shows how to translate such
-iterations into an Artificial Neural Network (ANN), in order to
-evaluate the capability for this latter to learn chaotic behaviors.
-This ability is studied in Sect.~\ref{section:experiments}, where
-various ANNs try to learn two sets of data: the first one is obtained
-by chaotic iterations while the second one results from a non-chaotic
-system. Prediction success rates are given and discussed for the two
-sets. The paper ends with a conclusion section where our contribution
-is summed up and intended future work is exposed.
-
+La section~\ref{S2} définit la construction d'un réseau de neurones
+chaotique selon Devanay. La section~\ref{S3} présente l'approche duale
+de vérification si un réseau de neurones est chaotique ou non.
+La section~\ref{sec:ann:approx} s'intéresse à étudier pratiquement
+si un réseau de
+neurones peut approximer des itérations unaires chaotiques,
+ces itérations
+étant obtenues à partir de fonctions issues de la démarche détaillée dans
+le chapitre précédent.
+Ce travail a été publié dans~\cite{bcgs12:ij}.