H. Cardot is a full professor at the University François Rabelais Tours in France since 2003. He received his PhD in 1993 from the University of Caen (France). He is head of the Pattern Recognition and Image Analysis group (20 researchers) of the LI research laboratory. His research focuses on pattern recognition and in particular neural networks and SVM for time series prediction. He teaches at the Engineers Polytechnic School of Tours.
The RNNs (Recurrent Neural Networks) are a general case of artificial neural networks where the connections are not feed-forward ones only. In RNNs, connections between units form directed cycles, providing an implicit internal memory. Those RNNs are adapted to problems dealing with signals evolving through time. Their internal memory gives them the ability to naturally take time into account. Valuable approximation results have been obtained for dynamical systems.
Go to the book