Programme

 PROGRAMME de la journée (aussi en pdf)

Master Class -  Christophe Garcia et Stefan Duffner du laboratoire LIRIS présenteront un bref historique de la recherche sur l'Intelligence Artificielle autour des réseaux de neurones. Quelques modèles et algorithmes fondamentaux, comme le perceptron multi-couches et la rétro-propagation du gradient ainsi que des architectures plus récentes, comme les réseaux de neurones profonds (Deep Learning), récurrents, résiduels et siamois, seront expliqués et illustrés par des exemples applicatifs.

Durant le temps de midi, autour d'un buffet, les participants pourront partager leurs expériences et leurs questions concernant la mise en oeuvre des méthodes d'apprentissage automatique et les réseaux de neurones. Les sujets méthodologiques ainsi que les aspects les pratiques jusqu'à la programmation seront partagés entre les participants.

L'après-midi sera consacrée à la résolution d'un problème concret posé à l'ensemble des participants. Olivier Bernard et François Varray animeront cette séance, ils s'appuieront sur des supports de cours, des exemples et du code disponible en ligne avant la journée. Sur place, les participants développeront du code Matlab pour résoudre un problème de reconnaissance de chiffres manuscripts  par réseaux de neurones.

Les intervenants :

Christophe Garcia has been working since 1991 in neural-based approaches for computer vision and specially since 1998 on convolutional neural networks for image analysis and understanding. He has been involved in numerous industrial and academic projects during his stays in several European major labs: IBM advanced technologies-France, Computer Vision Center of the Universitat Autonoma de Barcelona, German National Research Center in Bonn – GMD (now Fraunhofer Institute), Foundation for Research and Technology Hellas – FORTH - University of Crete, IRISA-INRIA-Texmex Rennes and from 2003 to 2010, as a Fellow Expert Researcher in France Telecom R&D (now Orange Labs) and manager of the Multimedia Content Analysis Technologies team. Since 2010, Christophe is Full Professor at INSA de Lyon. From 2011 to 2015, he has been head of the IMAGINE research team of the LIRIS laboratory. He is now Deputy Director of the LIRIS laboratory and Vice-President for Research in Information and Digital Society at Insa - Lyon. His current technical and research activities are in the areas of ConvNets for object recognition and tracking, neural networks for metric learning, non-linear embedding, pattern recognition and computer vision. He holds 17 industrial patents and has published more than 140 articles in international conferences and journals. He has served as an associate editor of International Journal of Visual Communication and Image Representation (Elsevier), Image and Video Processing (Hindawi) and Pattern Analysis and Application (Springer-Verlag). Since 2017, he acts as a vice-chair of the European program FET-OPEN - Research and Innovation Actions, in charge of the evaluation process.

Stefan Duffner received a Bachelor's degree in Computer Science from the University of Applied Sciences Konstanz, Germany in 2002 and a Master's degree in Applied Computer Science from the University of Freiburg, Germany in 2004.
He performed his dissertation research at Orange Labs in Rennes, France, on face image analysis with statistical machine learning methods, notably convolutional neural networks, and in 2008, he obtained a Ph.D. degree in Computer Science from the University of Freiburg.
He then worked for 4 years as a post-doctoral researcher at the Idiap Research Institute in Martigny, Switzerland, in the field of computer vision and video analysis for visual object tracking applications.
As of today, Stefan Duffner is an associate professor in the IMAGINE team of the LIRIS research lab at INSA Lyon.

François Varray  received the Diploma in engineering and the master’s degree in image and signal processing from the Ecole des Mines de Saint-Etienne, Saint-Étienne, France, in 2008, and the Ph.D. degree in nonlinear ultrasound simulation
from the Université de Lyon 1, Lyon, France, in 2011. His Ph.D. research was realized in co-agreement between the CREATIS, Lyon, and the MSD Laboratory, Florence, Italy, where he has been an Associate Professor since 2013. His current research interests include the nonlinear ultrasound propagation simulation, nonlinear image simulation, multiresolution motion estimation, cardiac imaging, and photoacoustic imaging. Recently, he participated to the developpement of 3-D+t ultrafast acquisition system.

Olivier Bernard has an MSc in Electrical Engineering and received a PhD in Medical Image Processing from the University of Lyon (INSA) - France - in 2006. In 2007, he became Associate Professor at the French University of Lyon and a member of the CREATIS laboratory (CNRS 5220, INSERM U1044, INSA-Lyon, University of Lyon). In 2013, he was a one year invited professor at Federal Polytechnic Institute of Lausanne (Switzerland) in the laboratory headed by Prof. Jean Philippe Thiran. He was an Associate Editor for the IEEE Transactions on Image Processing Journal between 2012 and 2016. His current research interests include medical image analysis with a particular attention to cardiac imaging. He has a strong interest in image reconstruction, image segmentation, motion analysis, statistical modeling, sampling theories and machine learning.