Publications

2018

Taking Apart Autoencoders: How do They Encode Geometric Shapes ?
- Newson Alasdair
- Almansa Andrés
- Gousseau Yann
- Ladjal Saïd
, 2018. We study the precise mechanisms which allow autoencoders to encode and decode a simple geometric shape, the disk. In this carefully controlled setting, we are able to describe the specific form of the optimal solution to the minimisation problem of the training step. We show that the autoencoder indeed approximates this solution during training. Secondly, we identify a clear failure in the generali-sation capacity of the autoencoder, namely its inability to interpolate data. Finally, we explore several regularisation schemes to resolve the generalisation problem. Given the great attention that has been recently given to the generative capacity of neural networks, we believe that studying in depth simple geometric cases sheds some light on the generation process and can provide a minimal requirement experimental setup for more complex architectures.
Estimation d'un circuit électrique équivalent, à résistances et capacités thermiques, d'un bâtiment pour le contrôle optimal du chauffage du bâtiment
- Nabil Tahar
- Jicquel Jean-Marc
- Girard Alexandre
- Roueff François
, 2018, pp.https://permalink.orbit.com/RenderStaticFirstPage?XPN=S5GmjW98%252BeXWqxLm4QBXD3fDUqlXTJ5uwQdFuycu4uk%3D%26n%3D1&id=0&base=FAMPAT. The invention relates to a method for determining a thermal model of a building equipped with a heating installation, in particular for energy diagnosis or optimization of the heating of said building, wherein: - An overall energy consumption load curve (CDC) is obtained from at least one energy consumption meter (COC), In predefined time steps, said load curve being capable of containing a consumption payload (Qu) for heating the building by said installation as well as a load for consumption needs not linked to the heating of the building, - And of one or more connected objects associated with respective appliances, which consume energy and are not controlled for a heat supply (ACN), at least one item of information on the switching on or off of said appliances (ACN), And time intervals are detected in the load curve (CDC) during which the connected objects inform of a stop state of the respective apparatuses, in order to obtain a first estimate of said payload (Qu), which makes it possible to iteratively correct the model for its optimization.
Generalization Bounds for Minimum Volume Set Estimation based on Markovian Data, ISAIM, International Symposium on Artificial Intelligence and Mathematics proceedings, 1-7
- Bertail Patrice
- Ciołek Gabriela
- Clémençon Stéphan
, 2018.
Mean value coordinates for quad cages in 3D
- Thiery Jean-Marc
- Memari Pooran
- Boubekeur Tamy
ACM Transactions on Graphics, Association for Computing Machinery, 2018.
Mathematical models for very high resolution SAR data and their applications
- Deledalle Charles-Alban
- Denis L.
- Ferraioli G.
- Tupin Florence
, 2018.
DyBED: An Efficient Algorithm for Updating Betweenness Centrality in Directed Dynamic Graphs
- Chehreghani Mostafa Haghir
- Bifet Albert
- Abdessalem Talel
, 2018, pp.2114-2123.
Quarante ans d’imagerie satellitaire radar
- Nicolas Jean-Marie
- Tupin Florence
Revue Française de Photogrammétrie et de Télédétection, Société Française de Photogrammétrie et de Télédétection, 2018.
Managing 'proto-ecosystems' - two smart mobility case studies
- Marcocchia Giulia
- Maniak Rémi
International Journal of Automotive Technology and Management, Inderscience, 2018, 18 (3), pp.209-228. This paper considers how ecosystem-based research projects can be managed for a successful deployment of systemic and disruptive innovation. Such projects are defined as assignments in which heterogeneous organisations must invest upfront, aiming at co-constructing a systemic offer with shared interest, shared uncertainty and high economic, environmental and social impacts. Innovation management, ecosystem, and public-private partnership literatures have been investigated, as well as two European Commission funded research projects aimed at smart mobility infrastructure development. Results show these projects are both critical and disappointing for each player. We explain this contradiction of value perception showing that partners need such ecosystem projects to go forward and update their competences and roadmaps, but that the observed project management approach hampers the collectively built learning and the evolution of the strategic agenda of each partner. In conclusion, we define the concept of proto-ecosystem as an intermediary 'management object' for innovation management, and point out implications to manage such projects in order to unfold their whole potential. (10.1504/IJATM.2018.093413)
DOI : 10.1504/IJATM.2018.093413
Method, device and computer program for encapsulating media data into a media file
- Denoual Franck
- Mazé Frédéric
- Le Feuvre J.
- Ouedraogo Nael
, 2018.
Musical Descriptions Based on Formal Concept Analysis and Mathematical Morphology
- Agon Carlos
- Andreatta Moreno
- Atif Jamal
- Bloch Isabelle
- Mascarade Pierre
, 2018, pp.105-119. In the context of mathematical and computational representations of musical structures, we propose algebraic models for formalizing and understanding the harmonic forms underlying musical compositions. These models make use of ideas and notions belonging to two algebraic approaches: Formal Concept Analysis (FCA) and Mathematical Morphology (MM). Concept lattices are built from interval structures whereas mathematical morphology operators are subsequently defined upon them. Special equivalence relations preserving the ordering structure of the lattice are introduced in order to define musically relevant quotient lattices modulo congruences. We show that the derived descrip-tors are well adapted for music analysis by taking as a case study Ligeti's String Quartet No. 2. (10.1007/978-3-319-91379-7_9)
DOI : 10.1007/978-3-319-91379-7_9
Profitable Bandits
- Achab Mastane
- Clémençon Stéphan
- Garivier Aurélien
Proceedings of Machine Learning Research, PMLR, 2018, 95, pp.694-709. Originally motivated by default risk management applications, this paper investigates a novel problem, referred to as the profitable bandit problem here. At each step, an agent chooses a subset of the K ≥ 1 possible actions. For each action chosen, she then respectively pays and receives the sum of a random number of costs and rewards. Her objective is to maximize her cumulated profit. We adapt and study three well-known strategies in this purpose, that were proved to be most efficient in other settings: kl-UCB, Bayes-UCB and Thompson Sampling. For each of them, we prove a finite time regret bound which, together with a lower bound we obtain as well, establishes asymptotic optimality in some cases. Our goal is also to compare these three strategies from a theoretical and empirical perspective both at the same time. We give simple, self-contained proofs that emphasize their similarities, as well as their differences. While both Bayesian strategies are automatically adapted to the geometry of information, the numerical experiments carried out show a slight advantage for Thompson Sampling in practice.
Mass volume curves and anomaly ranking
- Clémençon Stéphan
- Thomas Albert
Electronic Journal of Statistics, Shaker Heights, OH : Institute of Mathematical Statistics, 2018, 12 (2), pp.2806-2872. (10.1214/18-EJS1474)
DOI : 10.1214/18-EJS1474
Une approche par patchs, multi-atlas, itérative pour la segmentation du cortex cérébral en IRM néonatale
- Tor-Díez Carlos
- Passat Nicolas
- Bloch Isabelle
- Faisan Sylvain
- Bednarek Nathalie
- Rousseau François
, 2018. L’analyse des structures cérébrales chez le nouveau-né constitue un enjeu de santé majeur, notamment en cas de prématurité, afin de disposer d’informations prédictives sur le développement de l’enfant. Le cortex est, en particulier, une structure d’intérêt, observable en IRM (imagerie par résonance magnétique). Les données IRM néonatales présentent toutefois des spécificités qui les rendent complexes à traiter. Dans ce contexte, les approches multi-atlas constituent une stratégie efficace, tirant parti de données traitées préalablement. La méthode proposée dans cet article repose sur une telle stratégie multi-atlas. Elle s’appuie notamment sur deux paradigmes : l’utilisation d’un modèle non local à base de patchs, et l’utilisation d’un schéma d’optimisation itératif. L’usage couplé de ces deux concepts permet notamment de considérer des patchs liés à l’image ainsi qu’à sa segmentation courante. Cette stratégie, comparée à de précédentes méthodes multi-atlas de la littérature, aboutit à des résultats de segmentation corticale robustes.
Segmentation of pelvic vessels in pediatric MRI using a patch based learning approach
- Virzi Alessio
- Gori Pietro
- Muller Cécile
- Mille Eva
- Peyrot Quoc
- Berteloot Laureline
- Boddaert Nathalie
- Sarnacki Sabine
- Bloch Isabelle
, 2018, pp.617.
Transcription of Spanish Historical Handwritten Documents with Deep Neural Networks
- Granell Emilio
- Chammas Edgard
- Likforman-Sulem Laurence
- Martínez-Hinarejos Carlos-D
- Mokbel Chafic
- Cirstea Bogdan
Journal of Imaging, MDPI, 2018, 4 (1), pp.22.
A Smooth Primal-Dual Optimization Framework for Nonsmooth Composite Minimization
- Tran-Dinh Quoc
- Fercoq Olivier
- Cevher Volkan
SIAM Journal on Optimization, Society for Industrial and Applied Mathematics, 2018, 28 (1), pp.96-134. We propose a new first-order primal-dual optimization framework for a convex optimization template with broad applications. Our optimization algorithms feature optimal convergence guarantees under a variety of common structure assumptions on the problem template. Our analysis relies on a novel combination of three classic ideas applied to the primal-dual gap function: smoothing, acceleration, and homotopy. The algorithms due to the new approach achieve the best known convergence rate results, in particular when the template consists of only non-smooth functions. We also outline a restart strategy for the acceleration to significantly enhance the practical performance. We demonstrate relations with the augmented Lagrangian method and show how to exploit the strongly convex objectives with rigorous convergence rate guarantees. We provide numerical evidence with two examples and illustrate that the new methods can outperform the state-of-the-art, including Chambolle-Pock, and the alternating direction method-of-multipliers algorithms.
Attack Tree Construction and Its Application to the Connected Vehicle
- Danger Jean-Luc
- Karray Khaled
- Guilley Sylvain
- Abdelaziz Elaabid M.
, 2018, pp.175-190. (10.1007/978-3-319-98935-8_9)
DOI : 10.1007/978-3-319-98935-8_9
Ubiquitous Artificial Intelligence and Dynamic Data Streams
- Bifet Albert
- Read Jesse
, 2018, pp.1-6.
Far-from-Equilibrium Route to Superthermal Light in Bimodal Nanolasers
- Marconi Mathias
- Javaloyes Julien
- Hamel Philippe
- Raineri Fabrice
- Levenson Ariel
- Yacomotti Alejandro M.
Physical Review X, American Physical Society, 2018, 8 (1). (10.1103/PhysRevX.8.011013)
DOI : 10.1103/PhysRevX.8.011013
Regional Control of Probabilistic Cellular Automata
- Bagnoli Franco
- Dridi Sara
- El Yacoubi Samira
- Rechtman Raul
, 2018, 11115.
Preliminary study of CEDBT and CESM performances using simulated analytical contrast uptakes
- Sanchez de La Rosa Ruben
- Carton A.-K.
- Milioni de Carvalho P.
- Li Z.
- Muller S.
- Bloch Isabelle
, 2018, pp.792-795.
OP VI–2 Organ-specific integrative exposure assessment for radio-frequency electromagnetic fields: general population exposure and dose contribution of various sources
- van Wei Luuk
- Liorni I
- Capstick Myles
- Thielens Arno
- Aerts Sam
- Joseph W.
- Wiart Joe
- Cardis Elisabeth
- Vermeulen Roel
Occupational & Environmental Medicine, 2018, 75 (1). Background/aim The daily dose of radio-frequency electromagnetic fields (RF-EMF) received by the human body depends on source, use, and body characteristics. We developed a model capable of estimating total RF-EMF dose (J/kg) for 64 body tissues as well as the contribution of specific sources to total dose based on personal characteristics, source characteristics, and scenarios of use. Methods The Integrated Exposure Model (IEM) uses personal characteristics and scenarios of use to estimate daily RF-EMF dose from mobile phones, DECT phones, tablets, body area networks, laptops, on/near body devices, smartwatches, virtual reality headsets, WiFi routers, and far field sources. Specific absorption rates (SAR) in various tissues were calculated for each source using transfer algorithms based on source and body characteristics. These were then adjusted for scenarios of use. Lastly, the model calculated the integrative dose from all sources combined and the relative contribution of each source. To estimate population exposure levels, we used data from an online survey on use of mobile communication devices deployed in four countries (France, the Netherlands, Spain, Switzerland). Results The online survey resulted in a dataset of 1768 participants, with a mean age of 52 years. Preliminary results indicate an average whole body dose of 0.15 J/kg per day, and an average whole brain dose of 0.09 J/kg per day. Women tended to have slightly higher doses than men, particularly in the youngest age group, due to higher reported use of mobile phones for voice and data. Source specific contribution varied depending on tissue. For the brain, the highest contribution (32%) came from mobile phones. Phone, tablet, and WiFi use together account for 91% of total brain dose. For the whole body: phone data use, WiFi, tablet, and laptop use accounted for 97% of the average total dose in our population. Conclusion We developed a model capable of estimating integrative RF-EMF dose from both current and novel devices. Using survey data on device use we were able to estimate average whole brain (0.09 J/kg) and average whole body (0.15 J/kg) dose. Device output powers in various scenarios of use were found to strongly influence model results.
Computing Contrast on Conceptual Spaces
- Sileno Giovanni
- Bloch Isabelle
- Atif Jamal
- Dessalles Jean-Louis
, 2018, pp.11-25.
BGP Extended Communities LCAF Type
- Saucez Damien
- Iannone Luigi
, 2018.
Algorithms for concurrent systems
- Kuznetsov Petr
- Guerraoui Rachid
, 2018.

Retour aux années