JIRC 2017: Journée Informatique de Région Centre

JIRC are yearly workshops gathering the LIFO and the LIFAT laboratories. SInce 2015 they are organizd by the ICVL federation.

The 2017 edition will take place on Thursday, 14 December 2017 at the LIFO (see the directions):

• Laboratoire d'Informatique Fondamentale d'Orléans
• Batiment IIIA
• Rue Léonard de Vinci, 45067 Orléans
• LIFO, building IIIA; a.m.: Amphi Herbrand; p.m.: lab E07(+E06)

Program

8:40-8:45	Welcome
8:45-8:55	Opening, ICVL news
8:55-9:40	(session 1) Keynote: Radu Ciucanu gMark: Schema-Driven Generation of Graphs and Queries
9:40-10:00	coffee break
10:00-12:00	(session 2, chair: Benjamin Nguyen) Presentations of recent joint work 10:00-10:24 Thomas Devogele, Laurent Etienne, Emmanuel Melin, Sophie Robert, Optimisation et parallélisation de la distance de Fréchet 10:24-10:48 Alexis Puret, Jean-Yves Antoine, Anaïs Lefeuvre-Halftermeyer, Nicolas Labroche, Silvie Billot, Marcillio de Souto, Classification SVM (séparateurs à vaste marge) pour la résolution de la coréference 10:48-11:12 Than Binh Nguyen, Béatrice Bouchou-Markhoff, Jacques Chabin, Mirian Halfeld Ferrari Alves, Validating Data from Semantic Web Providers 11:12-11:34 Mustapha Bahma, Arnaud Giacometti, Dominique Li, Arnaud Soulet, Christel Vrain MapFIM : Memory Aware Parallelized Frequent Itemset Mining in Very Large Datasets 11:34-12:00 L. Bobelin, K. Durand, N. Fichot, A. Jousse, Y. Kergosien, M.E. Labat, A. Royer, C. Toinard, Aide à la planification de la prise en charge d’enfants handicapés moteurs
12:00-14:00	Lunch: l'Agora restaurant, 2 Rue de Tours, 45100 Orléans
14:00-15:30	(session 3, chair: Patrick Marcel) Invited tutorial (part 1): Jordi Vitria Let's open the black box of deep learning! (lecture + lab, part 1)
15:30-15:50	break
15:50-17:20	(session 3) Invited tutorial (part 2): Jordi Vitria Let's open the black box of deep learning! (lecture + lab, part 2)
17:20-17:30	Closing

Keynote speakers

• gMark: Schema-Driven Generation of Graphs and Queries

  Radu Ciucanu - Assistant Professor, Université Clermont Auvergne (France), LIMOS laboratory

  Abstract
  Massive graph data sets are pervasive in contemporary application domains. Hence, graph database systems are becoming increasingly important. In the experimental study of these systems, it is vital that the research community has shared solutions for the generation of database instances and query workloads having predictable and controllable properties. In this talk, I will present the design and engineering principles of gMark, a domain- and query language-independent graph instance and query workload generator. A core contribution of gMark is its ability to target and control the diversity of properties of both the generated instances and the generated workloads coupled to these instances. Further novelties include support for regular path queries, a fundamental graph query paradigm, and schema-driven selectivity estimation of queries. I will finally give an overview on an extension of gMark called EGG (Evolving Graph Generator), a framework for generating evolving RDF graphs based on finely-tuned temporal constraints given by the user.

  CV
  Radu Ciucanu est maître de conférences à l'Université Clermont Auvergne depuis 2016. Avant, il a été postdoc à l'Université d'Oxford et doctorant à l'Université de Lille et Inria. Ses recherches portent sur la gestion de données orientées graphes, la sécurité des calculs distribués dans le cloud, le web sémantique, l'intégration de données, et les interactions entre les bases de données et l'apprentissage automatique. Plus de détails sur sa page personnelle et sa page DBLP.

• Let's open the black box of deep learning!

  Jordi Vitrià - Full Professor at the Departement de Matemàtica Aplicada i Anàlisi of the Universitat de Barcelona

  Abstract
  Deep learning is one of the fastest growing areas of machine learning and a hot topic in both academia and industry. This lecture will try to figure out what are the real mechanisms that make this technique a breakthrough with respect to the past. To this end, we will review some of the most common architectures (CNN, LSTM, etc.) and their applications by following a hands-on approach. By the end of the lecture, attendants will be able to (i) describe how a neural network works and combine different types of layers and activation functions; (i) describe how these models can be applied in computer vision, text analytics, etc.; (iii) develop simple models in Tensorflow.

  CV
  Jordi Vitria joined the University of Barcelona (UB) in 2007 as Full Professor, where he teaches an introductory course on Algorithms and advanced courses on Data Science and Deep Learning. From April 2011 to January 2016 he served as Head of the Applied Mathematics and Analysis Department, UB. He is currently member of the new Mathematics & Computer Science Department at UB. Jordi's research, when personal computers had 128KB of memory, was originally oriented towards digital image analysis and how to extract quantitative information from them, but soon evolved towards computer vision problems. After a postdoctoral year at the University of California at Berkeley in 1993, Jordi focused on Bayesian methods for computer vision methods. Now, he is the head of a research group working in deep learning, computer vision and machine learning.

  Requirements for participants:
  Software installed on your personnal software in advance, following the instructions.

  Course material:

  • Lecture slides
  • Code and data for the lab session

Registration

Please, fill in the registration form by Thursday 23 November at 8 p.m. at latest.

Organisation committee

• Mirian Halfeld Ferrari (LIFO, Orléans)
• Agata Savary (LIFAT, Blois)
• Christelle Grange (LIFAT, Tours)
• Naly Raliravaka (LIFO, Orléans)