• Other research productsclose
• FR close
• English close
• HAL-Rennes 1 close

International audience; A recommendation – based on reviews by Lei Zhao, Yaniv Brandvain and one anonymous reviewer – of the article: Awad DA, Waller D (2022) Conditions for maintaining and eroding pseudo-overdominance and its contribution to inbreeding depression. bioRxiv, 2021.12.16.473022, ver. 3 peer-reviewed and recommended by Peer Community in Evolutionary Biology. https://doi.org/10.1101/2021.12.16.473022

Context of the tutorial: the IEEE CIS Summer School on Computational Intelligence and Applications (IEEE CIS SSoCIA 2022), associated with the 8th IEEE Latin American Conference on Computational Intelligence (IEEE LA-CCI 2022).; Doctoral; Random Neural Networks are a class of Neural Networks coming from Stochastic Processes and, in particular, from Queuing Models. They have some nice properties and they have reached good performances in several application areas. They are, in fact, queuing systems seen as Neural machines, and the two uses (probabilistic models for the performance evaluation of systems, or learning machines similar as the other more standard families of Neural Networks) refer to the same mathematical objects. They have the appealing that, as other special models that are unknown for most experts in Machine Learning, their testing in and/or adaptation to the many areas where standard Machine Learning techniques have obtained great successes is totally open.In the tutorial, we will introduce Random Neurons and the networks we can build with them, plus some details about the numerical techniques needed to learn with them. We will also underline the reasons that make them at least extremely interesting. We will also describe some of their successful applications, including our examples. We will focus on learning, but we will mention other uses of these models in performance evaluation, in the analysis of biological systems, and in optimization.

Doctoral; Decentralization and hybridization of distributed systems has given birth to edge and fog computing. At the same time, artificial intelligence and self-adaptive mechanisms have allowed great progress in the autonomy of networks. In this talk, we look at the need for self-organization, where local decisions give rise to globally consistent system behaviors. After introducing an overview of open questions, we illustrate our talk by presenting two algorithms for (1) target discovery following a disaster, using autonomous drones and for (2) extending the lifespan of an IoT network. Finally, we introduce a quick overview of some other recent works done.

Doctoral

Licence

International audience; Dear editors, we read with a great interest the Brief Communication entitled “Acoustic stimulation time-locked to the beginning of sleep apnea events reduces oxygen desaturations: a pilot-study”, by Waeber et al.

Blog - Le club des juristes

Slides decks:1. The Bond graph language (includes a comparison with Modelica's concept of potential and flow variables)2. Practice: reading & creating bond graphs3. Causality4. Short practice of causality; Engineering school; This short introductory course on Bond graph is part of a 36 hours course on Modelica & Bond graph (more precisely: multi-domain modeling, analysis and simulation with Modelica & Bond graph). It is an elective course at CentraleSupélec, campus of Rennes, offered in the 2nd year engineering curriculum (i.e. a Master 1 level course). Most of the course is devoted to Modelica (course material available at http://éole.net/courses/modelica/).This archive contains the material I used to teach a short introduction to Bond graph in a few hours since 2020. The course has only been taught two times, so the material is far from complete.See README in zip archive for a description of the folder.

Flash report sur le site de l'European social policy network, European commission

Flash report de l'European social policynetwork sur le site de la commission européenne