Search

Your search keyword '"Marc Schoenauer"' showing total 532 results
Start Over Author "Marc Schoenauer"

Refine your results

more »

more »

more »

more »
532 results on '"Marc Schoenauer"'

153. LEAP nets for system identification and application to power systems

Author

Patrick Panciatici, Antoine Marot, Benjamin Donnot, Zhengying Liu, Marc Schoenauer, Isabelle Guyon, and Balthazar Donon

Subjects
0209 industrial biotechnology, Operating point, Power transmission, Theoretical computer science, Artificial neural network, Computer science, Cognitive Neuroscience, System identification, 02 engineering and technology, Computer Science Applications, Electric power system, 020901 industrial engineering & automation, Artificial Intelligence, Causal inference, 0202 electrical engineering, electronic engineering, information engineering, Reinforcement learning, 020201 artificial intelligence & image processing, Transfer of learning
Abstract

Using neural network modeling, we address the problem of system identification for continuous multivariate systems, whose structures vary around an operating point. Structural changes in the system are of combinatorial nature, and some of them may be very rare; they may be actionable for the purpose of controlling the system. Although our ultimate goal is both system identification and control, we only address the problem of identification in this paper. We propose and study a novel neural network architecture called LEAP net, for Latent Encoding of Atypical Perturbation. Our method maps system structure changes to neural net structure changes, using structural actionable variables. We demonstrate empirically that LEAP nets can be trained with a natural observational distribution, very concentrated around a “reference” operating point of the system, and yet generalize to rare (or unseen) structural changes. We validate the generalization properties of LEAP nets theoretically in particular cases. We apply our technique to power transmission grids, in which high voltage lines are disconnected and re-connected with one-another from time to time, either accidentally or willfully. We discuss extensions of our approach to actionable variables, which are continuous (instead of discrete, in the case of our application) and make connections between our problem setting, transfer learning, causal inference, and reinforcement learning.

Published
2020

176. On Refining BERT Contextualized Embeddings using Semantic Lexicons

Author

Georgios Zervakis, Emmanuel Vincent, Miguel Couceiro, Marc Schoenauer, Knowledge representation, reasonning (ORPAILLEUR), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), TAckling the Underspecified (TAU), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), and Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)

Subjects
Contextualized embeddings, Retrofitting, Knowledge integration, Qualitative analysis, BERT, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience; Word vector representations play a fundamental role in many NLP applications. Exploiting human-curated knowledge was proven to improve the quality of word embeddings and their performance on many downstream tasks. Retrofitting is a simple and popular technique for refining distributional word embeddings based on relations coming from a semantic lexicon. Inspired by this technique, we present two methods for incorporating knowledge into contextualized embeddings. We evaluate these methods with BERT embeddings on three biomedical datasets for relation extraction and one movie review dataset for sentiment analysis. We demonstrate that the retrofitted vectors do not substantially impact the performance for these tasks, and conduct a qualitative analysis to provide further insights on this negative result.

Published
2021

177. Multi-resolution Graph Neural Networks for PDE Approximation

Author

Marc Schoenauer, Wenzhuo Liu, Mouadh Yagoubi, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria), IRT SystemX (IRT SystemX), IRT SystemX, TAckling the Underspecified (TAU), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Igor Farkaš, Paolo Masulli, Sebastian Otte, and Stefan Wermter

Subjects
Theoretical computer science, Computer science, Generalization, business.industry, Deep learning, Pooling, Image processing, 01 natural sciences, Convolutional neural network, 010305 fluids & plasmas, Domain (software engineering), 010101 applied mathematics, 0103 physical sciences, Graph (abstract data type), Polygon mesh, [INFO]Computer Science [cs], Artificial intelligence, Graph Neural Networks, Multi-resolution GNNs, 0101 mathematics, business, PDEs
Abstract

International audience; Deep Learning algorithms have recently received a growing interest to learn from examples of existing solutions and some accurate approximations of the solution of complex physical problems, in particular relying on Graph Neural Networks applied on a mesh of the domain at hand. On the other hand, state-of-the-art deep approaches of image processing use different resolutions to better handle the different scales of the images, thanks to pooling and up-scaling operations. But no such operators can be easily defined for Graph Convolutional Neural Networks (GCNN). This paper defines such operators based on meshes of different granularities. Multi-resolution GCNNs can then be defined. We propose the MGMI approach, as well as an architecture based on the famed U-Net. These approaches are experimentally validated on a diffusion problem, compared with projected CNN approach and the experiments witness their efficiency, as well as their generalization capabilities.

Published
2021

184. Partitionnement en régions linéaires pour la vérification formelle de réseaux de neurones

Author

Julien Henri-Aurélien Girard-Satabin, Aymeric Varasse, Guillaume Charpiat, Zakaria Chihani, Marc Schoenauer, Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)), Direction de Recherche Technologique (CEA) (DRT (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), TAckling the Underspecified (TAU), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Intégration des Systèmes et des Technologies (LIST), and CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-PF]Computer Science [cs]/Performance [cs.PF], [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

National audience; La grande polyvalence et les résultats impressionnants des réseaux de neurones modernes viennent en partie de leur non-linéarité. Cette propriété fondamentale rend malheureusement très difficile leur vérification formelle, et ce, même si on se restreint à une structure linéaire par morceaux. Cependant, chacune de ces régions linéaires prise indépendamment est simple à analyser. Nous proposons dans cet article une méthode permettant de simplifier le problème de vérification en opérant une séparation en multiples sous-problèmes linéaires. Nous présentons également des résultats concernant la structure de ces régions linéaires ainsi que leur similarité. Ce travail en cours démontre déjà la faisabilité de l'approche sur des problèmes simples ainsi que quelques expériences face à l'état de l'art.

Published
2021

185. Paradiseo: From a Modular Framework for Evolutionary Computation to the Automated Design of Metaheuristics ---22 Years of Paradiseo

Author

Alexandre Quemy, Johann Dreo, Juan J. Merelo, Arnaud Liefooghe, Benjamin Bouvier, Marc Schoenauer, Jan Gmys, and Sébastien Verel

Subjects
FOS: Computer and information sciences, 021103 operations research, Optimization problem, business.industry, Computer science, Distributed computing, 0211 other engineering and technologies, Computer Science - Neural and Evolutionary Computing, 02 engineering and technology, Modular design, computer.software_genre, Evolutionary computation, Software framework, Software, 0202 electrical engineering, electronic engineering, information engineering, Paradiseo, Computer Science - Mathematical Software, 020201 artificial intelligence & image processing, Algorithm design, Neural and Evolutionary Computing (cs.NE), business, Metaheuristic, computer, Mathematical Software (cs.MS), computer.programming_language
Abstract

The success of metaheuristic optimization methods has led to the development of a large variety of algorithm paradigms. However, no algorithm clearly dominates all its competitors on all problems. Instead, the underlying variety of landscapes of optimization problems calls for a variety of algorithms to solve them efficiently. It is thus of prior importance to have access to mature and flexible software frameworks which allow for an efficient exploration of the algorithm design space. Such frameworks should be flexible enough to accommodate any kind of metaheuristics, and open enough to connect with higher-level optimization, monitoring and evaluation softwares. This article summarizes the features of the ParadisEO framework, a comprehensive C++ free software which targets the development of modular metaheuristics. ParadisEO provides a highly modular architecture, a large set of components, speed of execution and automated algorithm design features, which are key to modern approaches to metaheuristics development., Comment: 12 pages, 6 figures, 3 listings, 1 table. To appear in 2021 Genetic and Evolutionary Computation Conference Companion (GECCO'21 Companion), July 10--14, 2021, Lille, France. ACM, New York, NY, USA

Published
2021
Full Text
View/download PDF

187. Neural Networks for Power Flow : Graph Neural Solver

Author

Antoine Marot, Rémy Clément, Marc Schoenauer, Balthazar Donon, Benjamin Donnot, Isabelle Guyon, Réseau de Transport d'Electricité [Paris] (RTE), TAckling the Underspecified (TAU), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Université Paris-Saclay, Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France

Subjects
Artificial neural network, Computer science, 020209 energy, Computation, 020208 electrical & electronic engineering, Probabilistic logic, Energy Engineering and Power Technology, 02 engineering and technology, Solver, AC power, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Electric power system, Power flow, Computer engineering, 0202 electrical engineering, electronic engineering, information engineering, Graph (abstract data type), Graph Neural Networks, Electrical and Electronic Engineering, Power Flow, Graph Neural Solver, Artificial Neural Networks
Abstract

International audience; Recent trends in power systems and those envisioned for the next few decades push Transmission System Operators to develop probabilistic approaches to risk estimation. However, current methods to solve power flows are too slow to fully attain this objective. Thus we propose a novel artificial neural network architecture that achieves a more suitable balance between computational speed and accuracy in this context. Improving on our previous work on Graph Neural Solver for Power System [10], our architecture is based on Graph Neural Networks and allows for fast and parallel computations. It learns to perform a power flow computation by directly minimizing the violation of Kirchhoff's law at each bus during training. Unlike previous approaches, our graph neural solver learns by itself and does not try to imitate the output of a Newton-Raphson solver. It is robust to variations of injections, power grid topology, and line characteristics. We experimentally demonstrate the viability of our approach on standard IEEE power grids (case9, case14, case30 and case118) both in terms of accuracy and computational time.

Published
2020

191. Automated Machine Learning with Monte-Carlo Tree Search

Author

Marc Schoenauer, Herilalaina Rakotoarison, Michèle Sebag, TAckling the Underspecified (TAU), Laboratoire de Recherche en Informatique (LRI), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Université Paris-Saclay, Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), This work was finded by the ADEME #1782C0034 project NEXT., CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, and CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Optimization problem, Computer science, Monte Carlo tree search, Machine Learning (stat.ML), 0102 computer and information sciences, 02 engineering and technology, Machine learning, computer.software_genre, 01 natural sciences, Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistics - Machine Learning, 0202 electrical engineering, electronic engineering, information engineering, Parametric statistics, Hyperparameter, business.industry, Bayesian optimization, Tree (data structure), 010201 computation theory & mathematics, Benchmark (computing), Portfolio, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer
Abstract

The AutoML approach aims to deliver peak performance from a machine learning portfolio on the dataset at hand. A Monte-Carlo Tree Search Algorithm Selection and Configuration (Mosaic) approach is presented to tackle this mixed (combinatorial and continuous) expensive optimization problem on the structured search space of ML pipelines. Extensive lesion studies are conducted to independently assess and compare: i) the optimization processes based on Bayesian Optimization or Monte Carlo Tree Search (MCTS); ii) its warm-start initialization based on meta-features or random runs; iii) the ensembling of the solutions gathered along the search. Mosaic is assessed on the OpenML 100 benchmark and the Scikit-learn portfolio, with statistically significant gains over AutoSkLearn, winner of all former AutoML challenges.

Published
2019

192. LEAP nets for power grid perturbations

Author

Donnot, B., Donon, B., Guyon, I., Liu, Z., Marot, A., Panciatici, P., Marc Schoenauer, TAckling the Underspecified (TAU), Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Réseau de Transport d'Electricité [Paris] (RTE), and Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France

Subjects
Signal Processing (eess.SP), FOS: Computer and information sciences, Computer Science - Machine Learning, Statistics - Machine Learning, [SPI.NRJ]Engineering Sciences [physics]/Electric power, FOS: Electrical engineering, electronic engineering, information engineering, Machine Learning (stat.ML), Electrical Engineering and Systems Science - Signal Processing, [STAT.OT]Statistics [stat]/Other Statistics [stat.ML], Machine Learning (cs.LG)
Abstract

International audience; We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to time, either accidentally or willfully. We call our architeture LEAP net, for Latent Encoding of Atypical Perturbation. Our method implements a form of transfer learning, permitting to train on a few source domains, then generalize to new target domains, without learning on any example of that domain. We evaluate the viability of this technique to rapidly assess cu-rative actions that human operators take in emergency situations, using real historical data, from the French high voltage power grid.

Published
2019

193. Artificial Evolution : 14th International Conference, Évolution Artificielle, EA 2019, Mulhouse, France, October 29–30, 2019, Revised Selected Papers

Author

Lhassane Idoumghar, Pierrick Legrand, Arnaud Liefooghe, Evelyne Lutton, Nicolas Monmarché, Marc Schoenauer, Lhassane Idoumghar, Pierrick Legrand, Arnaud Liefooghe, Evelyne Lutton, Nicolas Monmarché, and Marc Schoenauer

Subjects
Artificial intelligence, Algorithms, Numerical analysis, Computer networks, Computer engineering
Abstract

This book constitutes the thoroughly refereed post-conference proceedings of the 14th International Conference on Artificial Evolution, EA 2019, held in Mulhouse, France, in October 2019. The 16 revised papers were carefully reviewed and selected from 33 submissions. The papers cover a wide range of topics in the field of artificial evolution, such as evolutionary computation, evolutionary optimization, co-evolution, artificial life, population dynamics, theory, algorithmic and modeling, implementations, application of evolutionary paradigms to the real world (industry, biosciences...), other biologically-inspired paradigms (swarm, artificial ants, artificial immune systems, cultural algorithms...), memetic algorithms, multi-objective optimization, constraint handling, parallel algorithms, dynamic optimization, machine learning and hybridization with other soft computing techniques.

Published
2020

194. Algorithm Selector and Prescheduler in the ICON Challenge

Author

Michèle Sebag, Marc Schoenauer, and François Gonard

Subjects
Computer science, Population-based incremental learning, 02 engineering and technology, Simple (abstract algebra), Karloff–Zwick algorithm, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Combinatorial optimization, 020201 artificial intelligence & image processing, Algorithm design, Heuristics, Difference-map algorithm, Algorithm, FSA-Red Algorithm
Abstract

Algorithm portfolios are known to offer robust performances, efficiently overcoming the weakness of every single algorithm on some particular problem instances. Two complementary approaches to get the best out of an algorithm portfolio are to achieve algorithm selection (AS), and to define a scheduler, sequentially launching a few algorithms on a limited computational budget each. The presented system relies on the joint optimization of a pre-scheduler and a per-instance AS, selecting an algorithm well-suited to the problem instance at hand. ASAP has been thoroughly evaluated against the state-of-the-art during the ICON challenge for algorithm selection, receiving an honorable mention. Its evaluation on several combinatorial optimization benchmarks exposes surprisingly good results of the simple heuristics used; some extensions thereof are presented and discussed in the paper.

Published
2018

195. Optimization of computational budget for power system risk assessment

Author

Antoine Marot, Patrick Panciatici, Isabelle Guyon, Marc Schoenauer, Benjamin Donnot, TAckling the Underspecified (TAU), Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS), Réseau de Transport d'Electricité [Paris] (RTE), Université Paris-Sud - Paris 11 (UP11), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, and Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)

Subjects
FOS: Computer and information sciences, Power transmission, Artificial neural network, Computer science, Event (computing), 020209 energy, [SPI.NRJ]Engineering Sciences [physics]/Electric power, Probabilistic logic, Machine Learning (stat.ML), 02 engineering and technology, [STAT.OT]Statistics [stat]/Other Statistics [stat.ML], Grid, Machine Learning (cs.LG), Reliability engineering, Electric power system, Computer Science - Learning, Statistics - Machine Learning, 0202 electrical engineering, electronic engineering, information engineering, Benchmark (computing), Physical law
Abstract

We address the problem of maintaining high voltage power transmission networks in security at all time, namely anticipating exceeding of thermal limit for eventual single line disconnection (whatever its cause may be) by running slow, but accurate, physical grid simulators. New conceptual frameworks are calling for a probabilistic risk-based security criterion. However, these approaches suffer from high requirements in terms of computational resources. Here, we propose a new method to assess this risk while not increasing too much the computational cost. The proposed method uses both machine learning techniques (artificial neural networks) and more standard simulators based on physical laws (eg. Kirchoff's laws). More specifically we train neural networks to estimate the overall dangerousness of a grid state, and use only the slow but accurate simulator on the most dangerous detected event. A classical benchmark problem (matpower 118 buses test case) is used to show the strengths of the proposed method in the evaluation of the global risk of the grid.

Published
2018

196. Fast Power system security analysis with Guided Dropout

Author

Donnot, B., Guyon, I., Marc Schoenauer, Marot, A., Panciatici, P., Réseau de Transport d'Electricité [Paris] (RTE), TAckling the Underspecified (TAU), Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, and Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)

Subjects
FOS: Computer and information sciences, Computer Science - Learning, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistics - Machine Learning, [SPI.NRJ]Engineering Sciences [physics]/Electric power, Machine Learning (stat.ML), Machine Learning (cs.LG)
Abstract

We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation solvers. We use a deep feed-forward neural network trained with load-flows precomputed by simulation. Our architecture permits to train a network on so-called "n-1" problems, in which load flows are evaluated for every possible line disconnection, then generalize to "n-2" problems without retraining (a clear advantage because of the combinatorial nature of the problem). To that end, we developed a technique bearing similarity with "dropout", which we named "guided dropout"., European Symposium on Artificial Neural Networks, Apr 2018, Bruges, Belgium

Published
2018

197. The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities

Author

Léni K. Le Goff, Simon Thibault, Antoine Fŕenoy, Sara Mitri, Peter Krcah, Charles Ofria, Laurent Keller, Marc Schoenauer, Stéphane Doncieux, Patryk Chrabaszcz, Carole Knibbe, Jeff Clune, Guillaume Beslon, Samuel Bernard, François Taddei, Robert T. Pennock, David M. Bryson, Anh Nguyen, Robert Feldt, Stephanie Forrest, William F. Punch, Carlos Maestre, Lee Altenberg, Hod Lipson, David E. Moriarty, Antoine Cully, Christoph Adami, Westley Weimer, Jason Yosinski, Frank Hutter, Thomas S. Ray, Marc Parizeau, Jean-Baptiste Mouret, Julie Beaulieu, Peter J. Bentley, Fred C. Dyer, Risto Miikkulainen, Karl Sims, Nick Cheney, David P. Parsons, Laura M. Grabowski, Eric Schulte, Dusan Misevic, Joel Lehman, Richard E. Lenski, Babak Hodjat, Christian Gagné, Robert MacCurdy, Kenneth O. Stanley, Richard A. Watson, Danesh Tarapore, Kai Olav Ellefsen, Stephan Fischer, Uber AI Labs, University of Wyoming (UW), Centre de Recherches Interdisciplinaires [Paris] (CRI), Michigan State University [East Lansing], Michigan State University System, Laboratoire de Vision et Systèmes Numériques (LVSN), Université Laval [Québec] (ULaval), University College of London [London] (UCL), Institut Camille Jordan [Villeurbanne] (ICJ), École Centrale de Lyon (ECL), Université de Lyon-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Artificial Evolution and Computational Biology (BEAGLE), Laboratoire de Biométrie et Biologie Evolutive - UMR 5558 (LBBE), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS)-Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Imperial College London, Institut des Systèmes Intelligents et de Robotique (ISIR), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), University of Oslo (UiO), Blekinge Institute of Technology [Karlskrona] (BTH), The University of New Mexico [Albuquerque], Department of Integrative Biology [Zurich], State University of New York (SUNY), sentient technologies [San Francisco], Université de Lausanne (UNIL), Charles University [Prague] (CU), Columbia University [New York], University of Colorado [Boulder], Department of Fundamental Microbiology [Lausanne], Apple Inc, Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment (LARSEN), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Complex Systems, Artificial Intelligence & Robotics (LORIA - AIS), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Norwegian University of Science and Technology [Trondheim] (NTNU), Norwegian University of Science and Technology (NTNU), SED [Grenoble], Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), University of Oklahoma (OU), TAckling the Underspecified (TAU), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Department of Applied Mathematics (MIT), Massachusetts Institute of Technology (MIT), University of Central Florida [Orlando] (UCF), University of Southampton, University of Virginia [Charlottesville], National Science Foundation (NSF)NSF - Office of the Director (OD)CAREER: 1453549, Institut Camille Jordan (ICJ), Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Centre National de la Recherche Scientifique (CNRS), Modélisation mathématique, calcul scientifique (MMCS), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Centre National de la Recherche Scientifique (CNRS)-École Centrale de Lyon (ECL), Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire de Biométrie et Biologie Evolutive - UMR 5558 (LBBE), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS), Biologie Computationnelle et Mathématique (TIMC-IMAG-BCM), Techniques de l'Ingénierie Médicale et de la Complexité - Informatique, Mathématiques et Applications Grenoble - UMR 5525 (TIMC-IMAG), VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA)-VetAgro Sup - Institut national d'enseignement supérieur et de recherche en alimentation, santé animale, sciences agronomiques et de l'environnement (VAS)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA), Université de Lausanne = University of Lausanne (UNIL), Service Expérimentation et Développement (SED [Grenoble]), University of Virginia, Robustesse et évolvabilité de la vie (U1001), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris Descartes - Paris 5 (UPD5), Université Laval, Laboratoire des Multimatériaux et Interfaces (LMI), Université de Lyon-Université de Lyon-Centre National de la Recherche Scientifique (CNRS), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Inria Grenoble - Rhône-Alpes, Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA), Charles University [Prague], Laboratoire de Recherche en Informatique (LRI), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, and University of Central Florida [Orlando]

Subjects
FOS: Computer and information sciences, Technology, Surprise, 1702 Cognitive Sciences, 02 engineering and technology, Computer Science, Artificial Intelligence, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Creativity, DESIGN, Life, ROBUSTNESS, 0202 electrical engineering, electronic engineering, information engineering, Natural (music), Artificial Intelligence & Image Processing, Sociology, ADAPTATION, media_common, Cognitive science, 0303 health sciences, Experimental evolution, Computer Science - Neural and Evolutionary Computing, Biological Evolution, ROBOTS, Wonder, GENOME, evolutionary computation, 020201 artificial intelligence & image processing, Algorithms, STRATEGIES, media_common.quotation_subject, digital evolution, TERM, General Biochemistry, Genetics and Molecular Biology, Evolutionary computation, genetic algorithms, 03 medical and health sciences, Computer Science, Theory & Methods, Artificial Intelligence, Artificial life, 0801 Artificial Intelligence and Image Processing, Narrative, experimental evolution, Neural and Evolutionary Computing (cs.NE), 030304 developmental biology, Science & Technology, COMPLEXITY, Computational Biology, Computer Science, RADIATION
Abstract

International audience; Evolution provides a creative fount of complex and subtle adaptations that often surprise the scientists who discover them. However, the creativity of evolution is not limited to the natural world: artificial organisms evolving in computational environments have also elicited surprise and wonder from the researchers studying them. The process of evolution is an algorithmic process that transcends the substrate in which it occurs. Indeed, many researchers in the field of digital evolution can provide examples of how their evolving algorithms and organisms have creatively subverted their expectations or intentions, exposed unrecognized bugs in their code, produced unexpectedly adaptations, or engaged in behaviors and outcomes uncannily convergent with ones found in nature. Such stories routinely reveal surprise and creativity by evolution in these digital worlds, but they rarely fit into the standard scientific narrative. Instead they are often treated as mere obstacles to be overcome, rather than results that warrant study in their own right. Bugs are fixed, experiments are refocused, and one-off surprises are collapsed into a single data point. The stories themselves are traded among researchers through oral tradition, but that mode of information transmission is inefficient and prone to error and outright loss. Moreover, the fact that these stories tend to be shared only among practitioners means that many natural scientists do not realize how interesting and lifelike digital organisms are and how natural their evolution can be. To our knowledge, no collection of such anecdotes has been published before. This paper is the crowd-sourced product of researchers in the fields of artificial life and evolutionary computation who have provided first-hand accounts of such cases. It thus serves as a written, fact-checked collection of scientifically important and even entertaining stories. In doing so we also present here substantial evidence that the existence and importance of evolutionary surprises extends beyond the natural world, and may indeed be a universal property of all complex evolving systems.

Published
2018

198. Anticipating contingengies in power grids using fast neural net screening

Author

Antoine Marot, Marc Schoenauer, Patrick Panciatici, Benjamin Donnot, Isabelle Guyon, TAckling the Underspecified (TAU), Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Réseau de Transport d'Electricité [Paris] (RTE), Université Paris-Saclay, Université Paris-Sud - Paris 11 (UP11), Chalearn, and Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France

Subjects
FOS: Computer and information sciences, Physics - Physics and Society, Power transmission, Artificial neural network, Computer science, 020209 energy, [SPI.NRJ]Engineering Sciences [physics]/Electric power, Probabilistic logic, FOS: Physical sciences, Machine Learning (stat.ML), 02 engineering and technology, Physics and Society (physics.soc-ph), [STAT.OT]Statistics [stat]/Other Statistics [stat.ML], Reliability engineering, Power (physics), Residual risk, Electric power transmission, Statistics - Machine Learning, 0202 electrical engineering, electronic engineering, information engineering, Benchmark (computing), [PHYS.PHYS.PHYS-DATA-AN]Physics [physics]/Physics [physics]/Data Analysis, Statistics and Probability [physics.data-an]
Abstract

We address the problem of maintaining high voltage power transmission networks in security at all time. This requires that power flowing through all lines remain below a certain nominal thermal limit above which lines might melt, break or cause other damages. Current practices include enforcing the deterministic "N-1" reliability criterion, namely anticipating exceeding of thermal limit for any eventual single line disconnection (whatever its cause may be) by running a slow, but accurate, physical grid simulator. New conceptual frameworks are calling for a probabilistic risk based security criterion and are in need of new methods to assess the risk. To tackle this difficult assessment, we address in this paper the problem of rapidly ranking higher order contingencies including all pairs of line disconnections, to better prioritize simulations. We present a novel method based on neural networks, which ranks "N-1" and "N-2" contingencies in decreasing order of presumed severity. We demonstrate on a classical benchmark problem that the residual risk of contingencies decreases dramatically compared to considering solely all "N-1" cases, at no additional computational cost. We evaluate that our method scales up to power grids of the size of the French high voltage power grid (over 1000 power lines)., Comment: IEEE WCCI 2018, Jul 2018, Rio de Janeiro, Brazil. 2018

Published
2018
Full Text
View/download PDF

199. Tutorials at PPSN 2018

Author

Carola Doerr, Stjepan Picek, Mike Preuss, Will N. Browne, Michael Emmerich, Dirk Sudholt, Su Nguyen, Ana L. C. Bazzan, Pascal Kerschke, Domagoj Jakobovic, Ofer M. Shir, Nelishia Pillay, Alberto Moraglio, Ankur Sinha, Mengjie Zhang, Kalyanmoy Deb, Antonio J. Nebro, Yi Mei, Xiaodong Li, Krzysztof Krawiec, Juan J. Merelo, Marc Schoenauer, Saemundur O. Haraldsson, Pekka Malo, Per Kristian Lehre, Gisele L. Pappa, Michael G. Epitropakis, Pietro S. Oliveto, Darrell Whitley, Roman Senkerik, Gabriela Ochoa, Marko Ðurasević, Andrei Lissovoi, John R. Woodward, Julian F. Miller, Luis Martí, and Mark Wineberg

Subjects
Computer engineering, Computer science, Evolutionary computation, Field (computer science), Range (computer programming)
Abstract

PPSN 2018 features a total of 23 free tutorials covering a broad range of topics in evolutionary computation and related areas. From theory and methods to applications and computer implementations, and from introductory to advanced, the PPSN 2018 tutorial program offers participants the opportunity to learn more about both well-established and ongoing research in this field.

Published
2018

200. Artificial Evolution : 13th International Conference, Évolution Artificielle, EA 2017, Paris, France, October 25–27, 2017, Revised Selected Papers

Author

Evelyne Lutton, Pierrick Legrand, Pierre Parrend, Nicolas Monmarché, Marc Schoenauer, Evelyne Lutton, Pierrick Legrand, Pierre Parrend, Nicolas Monmarché, and Marc Schoenauer

Subjects
Artificial intelligence, Algorithms, Computer science—Mathematics, Discrete mathematics, Numerical analysis
Abstract

This book constitutes the thoroughly refereed post-conference proceedings of the 13th International Conference on Artificial Evolution, EA 2017, held in Paris, France, in October 2017. The 16 revised papers were carefully reviewed and selected from 33 submissions. The papers cover a wide range of topics in the field of artificial evolution, such as evolutionary computation, evolutionary optimization, co-evolution, artificial life, population dynamics, theory, algorithmics and modeling, implementations, application of evolutionary paradigms to the real world (industry, biosciences,...), other biologically-inspired paradigms (swarm, artificial ants, artificial immune systems, cultural algorithms...), memetic algorithms, multi-objective optimisation, constraint handling, parallel algorithms,, dynamic optimization, machine learning and hybridization with other soft computing techniques.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results