Search

Showing total 17 results
Start Over Topic [info.info-ai]computer science [cs]/artificial intelligence [cs.ai]
17 results

1. A Sparsity-promoting Dictionary Model for Variational Autoencoders

Author

Sadeghi, Mostafa, Magron, Paul, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), 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), and Experiments presented in this paper were carried out using the Grid’5000 testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr).

Subjects
FOS: Computer and information sciences, Sound (cs.SD), Computer Science - Machine Learning, generative models, sparsity, speech spectrogram modeling, Computer Science - Sound, Machine Learning (cs.LG), variational autoencoders, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Statistics::Machine Learning, Audio and Speech Processing (eess.AS), dictionary model, FOS: Electrical engineering, electronic engineering, information engineering, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Structuring the latent space in probabilistic deep generative models, e.g., variational autoencoders (VAEs), is important to yield more expressive models and interpretable representations, and to avoid overfitting. One way to achieve this objective is to impose a sparsity constraint on the latent variables, e.g., via a Laplace prior. However, such approaches usually complicate the training phase, and they sacrifice the reconstruction quality to promote sparsity. In this paper, we propose a simple yet effective methodology to structure the latent space via a sparsity-promoting dictionary model, which assumes that each latent code can be written as a sparse linear combination of a dictionary's columns. In particular, we leverage a computationally efficient and tuning-free method, which relies on a zero-mean Gaussian latent prior with learnable variances. We derive a variational inference scheme to train the model. Experiments on speech generative modeling demonstrate the advantage of the proposed approach over competing techniques, since it promotes sparsity while not deteriorating the output speech quality., Proc. of Interspeech 2022

Published
2022

2. Improving Sound Event Detection with Auxiliary Foreground-Background Classification and Domain Adaptation

Author

Olvera, Michel, Vincent, Emmanuel, Gasso, Gilles, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), 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), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Université Le Havre Normandie (ULH), Normandie Université (NU)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA), This work was made with the support of the French National Research Agency, in the framework of the project LEAUDS 'Learning to understandaudio scenes' (ANR-18-CE23-0020). Experiments presented in this paper were carried out using the Grid’5000 testbed, supported by a scientificinterest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr)., GRID5000, ANR-18-CE23-0020,LEAUDS,Apprentissage statistique pour la compréhension de scènes audio(2018), 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), and 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)

Subjects
sound event detection, semi-supervised learning, optimal transport, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, domain adaptation, [INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD], ambient sound scenes, unsupervised domain adaptation, [INFO]Computer Science [cs], foreground-background classification, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience; In this paper we provide two methods that improve the detection of sound events in domestic environments. First, motivated by the broad categorization of domestic sounds as foreground or background events according to their spectro-temporal structure, we propose to learn a foreground-background classifier jointly with the sound event classifier in a multi-task fashion to improve the generalization of the latter. Second, while the semi-supervised learning capability adopted for training sound event detection systems with synthetic labeled data and unlabeled or partially labeled real data aims to learn invariant representations for both domains, there is still a gap in performance when testing such systems on real environments. To further reduce this data mismatch, we propose a domain adaptation strategy that aligns the empirical distributions of the feature representations of active and inactive frames of synthetic and real recordings via optimal transport. We show that these two approaches lead to enhanced detection performance in terms of the event-based macro F1-score on the DESED dataset.

Published
2021

3. TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL

Author

Romac, Clément, Portelas, Rémy, Hofmann, Katja, Oudeyer, Pierre-Yves, Flowing Epigenetic Robots and Systems (Flowers), Inria Bordeaux - Sud-Ouest, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Unité d'Informatique et d'Ingénierie des Systèmes (U2IS), École Nationale Supérieure de Techniques Avancées (ENSTA Paris)-École Nationale Supérieure de Techniques Avancées (ENSTA Paris), Microsoft Research [Cambridge] (Microsoft), Microsoft Research, This work was supported by Microsoft Research through its PhD Scholarship Programme. Experiments presented in this paper were carried out using 1) the PlaFRIM experimental testbed, supported by Inria, CNRS (LABRI and IMB), Universite de Bordeaux, Bordeaux INP and Conseil Régional d’Aquitaine (see https://www.plafrim.fr/), 2) the computing facilities MCIA (Mesocentre de Calcul Intensif Aquitain) of the Université de Bordeaux and of the Université de Pau et des Pays de l’Adour, and 3) the HPC resources of IDRIS under the allocation 2020-[A0091011996] made by GENCI., Meila, Marina and Zhang, Tong, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Computer Science - Machine Learning, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience; Training autonomous agents able to generalize to multiple tasks is a key target of Deep Reinforcement Learning (DRL) research. In parallel to improving DRL algorithms themselves, Automatic Curriculum Learning (ACL) study how teacher algorithms can train DRL agents more efficiently by adapting task selection to their evolving abilities. While multiple standard benchmarks exist to compare DRL agents, there is currently no such thing for ACL algorithms. Thus, comparing existing approaches is difficult, as too many experimental parameters differ from paper to paper. In this work, we identify several key challenges faced by ACL algorithms. Based on these, we present TeachMyAgent (TA), a benchmark of current ACL algorithms leveraging procedural task generation. It includes 1) challengespecific unit-tests using variants of a procedural Box2D bipedal walker environment, and 2) a new procedural Parkour environment combining most ACL challenges, making it ideal for global performance assessment. We then use TeachMyAgent to conduct a comparative study of representative existing approaches, showcasing the competitiveness of some ACL algorithms that do not use expert knowledge. We also show that the Parkour environment remains an open problem. We open-source our environments, all studied ACL algorithms (collected from open-source code or re-implemented), and DRL students in a Python package available at https://github. com/flowersteam/TeachMyAgent.

Published
2021

4. Interdisciplinary Research in Artificial Intelligence: Challenges and Opportunities

Author

Remy Kusters, Dusan Misevic, Hugues Berry, Antoine Cully, Yann Le Cunff, Loic Dandoy, Natalia Díaz-Rodríguez, Marion Ficher, Jonathan Grizou, Alice Othmani, Themis Palpanas, Matthieu Komorowski, Patrick Loiseau, Clément Moulin Frier, Santino Nanini, Daniele Quercia, Michele Sebag, Françoise Soulié Fogelman, Sofiane Taleb, Liubov Tupikina, Vaibhav Sahu, Jill-Jênn Vie, Fatima Wehbi, Centre de Recherche Interdisciplinaire / Center for Research and Interdisciplinarity [Paris, France] (CRI), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris Cité (UPCité), Artificial Evolution and Computational Biology (BEAGLE), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), 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)-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 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)-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), Imperial College London, Institut de Génétique et Développement de Rennes (IGDR), Université de Rennes (UR)-Centre National de la Recherche Scientifique (CNRS)-Structure Fédérative de Recherche en Biologie et Santé de Rennes ( Biosit : Biologie - Santé - Innovation Technologique ), Flowing Epigenetic Robots and Systems (Flowers), Inria Bordeaux - Sud-Ouest, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), École Nationale Supérieure de Techniques Avancées (ENSTA Paris), Laboratoire Images, Signaux et Systèmes Intelligents (LISSI), Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12), Institut Universitaire de France (IUF), Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche (M.E.N.E.S.R.), Performance analysis and optimization of LARge Infrastructures and Systems (POLARIS), 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 d'Informatique de Grenoble (LIG), 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)-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), Nokia Bell Labs [Cambridge], 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), Hub France IA, Nokia Bell Labs [Paris-Saclay], Scool (Scool), Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Thanks to the Bettencourt Schueller Foundation long term partnership, the workshop that gave rise to this paper was partially supported by the funding from CRI Research Collaboratory, Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Paris (UP), 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)-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), Structure Fédérative de Recherche en Biologie et Santé de Rennes ( Biosit : Biologie - Santé - Innovation Technologique )-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Unité d'Informatique et d'Ingénierie des Systèmes (U2IS), École Nationale Supérieure de Techniques Avancées (ENSTA Paris)-École Nationale Supérieure de Techniques Avancées (ENSTA Paris), Université de Rennes 1 (UR1), and Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Centre National de la Recherche Scientifique (CNRS)-Structure Fédérative de Recherche en Biologie et Santé de Rennes ( Biosit : Biologie - Santé - Innovation Technologique )

Subjects
Big Data, 0301 basic medicine, [SCCO.COMP]Cognitive science/Computer science, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 03 medical and health sciences, 0302 clinical medicine, Political science, Health care, Computer Science (miscellaneous), auditability, education, lcsh:T58.5-58.64, Ai education, business.industry, lcsh:Information technology, interdisciplinary science, Precision medicine, artificial intelligence, Transparency (behavior), ethics, Variety (cybernetics), 030104 developmental biology, [INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA], Perspective, Artificial intelligence, business, interpretability, 030217 neurology & neurosurgery, Information Systems
Abstract

The use of artificial intelligence (AI) in a variety of research fields is speeding up multiple digital revolutions, from shifting paradigms in healthcare, precision medicine and wearable sensing, to public services and education offered to the masses around the world, to future cities made optimally efficient by autonomous driving. When a revolution happens, the consequences are not obvious straight away, and to date, there is no uniformly adapted framework to guide AI research to ensure a sustainable societal transition. To answer this need, here we analyze three key challenges to interdisciplinary AI research, and deliver three broad conclusions: 1) future development of AI should not only impact other scientific domains but should also take inspiration and benefit from other fields of science, 2) AI research must be accompanied by decision explainability, dataset bias transparency as well as development of evaluation methodologies and creation of regulatory agencies to ensure responsibility, and 3) AI education should receive more attention, efforts and innovation from the educational and scientific communities. Our analysis is of interest not only to AI practitioners but also to other researchers and the general public as it offers ways to guide the emerging collaborations and interactions toward the most fruitful outcomes.

Published
2020
Full Text
View/download PDF

5. Planification Monte Carlo orientée information

Author

Thomas, Vincent, Hutin, Gérémy, Buffet, Olivier, 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), École normale supérieure - Lyon (ENS Lyon), Experiments presented in this paper were carried out using the Grid’5000 testbed, supported by a scientific interest group hostedby Inria and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr)., École normale supérieure de Lyon (ENS de Lyon), and Thomas, Vincent

Subjects
[INFO.INFO-SY] Computer Science [cs]/Systems and Control [cs.SY], [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Planification dans l'incertain, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], recherche active d'information, [INFO.INFO-SY]Computer Science [cs]/Systems and Control [cs.SY], MCTS, POMDP, rho-POMDP, ComputingMethodologies_ARTIFICIALINTELLIGENCE, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience; Dans cet article, nous nous intéressons à la résolution de problèmes de collecte active d'information exprimés sous la forme de rho-POMDP, une extension des Processus Décisionnels de Markov Partiellement Observables (POMDP) dont la récompense rho dépend de l'état de croyance. Des approches utilisées pour résoudre les POMDP ont déjà été étendues au cadre rho-POMDP lorsque la récompense rho est convexe ou lipschtizienne, mais ces approches ne permettent pas de résoudre toutes les instances de rho-POMDP. Afin de proposer un algorithme en-ligne efficace qui s'affranchit des contraintes sur rho, cet article se concentre sur les méthodes à base de recherche arborescente Monte Carlo et cherche à adapter POMCP à la résolution de rho-POMDP. Comme les récompenses dépendent de l'état de croyance, il est nécessaire de modifier POMCP (i) pour échantillonner plusieurs états lors des trajectoires suivies et (ii) pour éviter les biais dans l'estimation des valeurs. Des expériences ont été conduites pour étudier les propriétés de l'approche proposée.

Published
2020

6. The trainer, the verifier, the imitator: Three ways in which human platform workers support artificial intelligence

Author

Paola Tubaro, Antonio A. Casilli, Marion Coville, 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 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), Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Institutions et Dynamiques Historiques de l'Économie et de la Société (IDHES), Université Paris 1 Panthéon-Sorbonne (UP1)-Université Paris 8 Vincennes-Saint-Denis (UP8)-Université Paris Nanterre (UPN)-Université d'Évry-Val-d'Essonne (UEVE)-Centre National de la Recherche Scientifique (CNRS)-Ecole Normale Supérieure Paris-Saclay (ENS Paris Saclay), Sociologie Information-Communication Design (SID), Institut interdisciplinaire de l’innovation de Telecom Paris (I3 SES), Télécom ParisTech-Institut interdisciplinaire de l’innovation (I3), Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS)-Télécom ParisTech-Institut interdisciplinaire de l’innovation (I3), Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Département Sciences Economiques et Sociales (SES), Télécom ParisTech, Institut Polytechnique de Paris (IP Paris), Institut d'Administration des Entreprises (IAE) - Poitiers (IAE Poitiers), Université de Poitiers, CEntre de REcherche en GEstion - EA 1722 (CEREGE), Université de Poitiers-Université de Poitiers-Université de Poitiers-La Rochelle Université (ULR), This paper presents results of a larger study called Digital Platform Labour (DiPLab), co-funded by Maison des Sciences de l’Homme Paris-Saclay, Force Ouvrière, a workers’ union, as part of a grant from Institut de recherches économiques et sociales (IRES), and France Stratégie, a service of the French Prime Minister’s office. The platform Foule Factory offered logistical support, and Inria provided complementary funding. For more information: http://diplab.eu, Ecole Normale Supérieure Paris-Saclay (ENS Paris Saclay)-Université d'Évry-Val-d'Essonne (UEVE)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Nanterre (UPN)-Université Paris 8 Vincennes-Saint-Denis (UP8)-Université Paris 1 Panthéon-Sorbonne (UP1), Institut interdisciplinaire de l’innovation (I3, une unité mixte de recherche CNRS (UMR 9217)), Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X)-Télécom ParisTech-MINES ParisTech - École nationale supérieure des mines de Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X)-Télécom ParisTech-MINES ParisTech - École nationale supérieure des mines de Paris, Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Université de Poitiers-Université de Poitiers-Université de Poitiers-Université de La Rochelle (ULR), École polytechnique (X)-Télécom ParisTech-Mines Paris - PSL (École nationale supérieure des mines de Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X)-Télécom ParisTech-Mines Paris - PSL (École nationale supérieure des mines de Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), and École polytechnique (X)-Télécom ParisTech-MINES ParisTech - École nationale supérieure des mines de Paris

Subjects
Information Systems and Management, Computer science, Trainer, Big data, 050801 communication & media studies, lcsh:A, Library and Information Sciences, micro-work, Digital platform labour, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 0508 media and communications, datafied production processes, 0502 economics and business, 050207 economics, Focus (computing), [SHS.SOCIO]Humanities and Social Sciences/Sociology, business.industry, Communication, 05 social sciences, artificial intelligence, [SHS.ECO]Humanities and Social Sciences/Economics and Finance, Computer Science Applications, machine learning, Artificial intelligence, lcsh:General Works, business, Information Systems
Abstract

International audience; This paper sheds light on the role of digital platform labour in the development of today's artificial intelligence, predicated on data-intensive machine learning algorithms. Focus is on the specific ways in which outsourcing of data tasks to myriad 'micro-workers', recruited and managed through specialized platforms, powers virtual assistants, self-driving vehicles and connected objects. Using qualitative data from multiple sources, we show that micro-work performs a variety of functions, between three poles that we label, respectively, 'artificial intelligence preparation', 'artificial intelligence verification' and 'artificial intelligence impersonation'. Because of the wide scope of application of micro-work, it is a structural component of contemporary artificial intelligence production processes - not an ephemeral form of support that may vanish once the technology reaches maturity stage. Through the lens of micro-work, we prefigure the policy implications of a future in which data technologies do not replace human workforce but imply its marginalization and precariousness.

Published
2020
Full Text
View/download PDF

7. Computing AES related-key differential characteristics with constraint programming

Author

Christine Solnon, Marine Minier, David Gerault, Pascal Lafourcade, Université Clermont Auvergne [2017-2020] (UCA [2017-2020]), Laboratoire d'Informatique, de Modélisation et d'optimisation des Systèmes (LIMOS), SIGMA Clermont (SIGMA Clermont)-Université d'Auvergne - Clermont-Ferrand I (UdA)-Ecole Nationale Supérieure des Mines de St Etienne-Centre National de la Recherche Scientifique (CNRS)-Université Blaise Pascal - Clermont-Ferrand 2 (UBP), Cryptology, arithmetic : algebraic methods for better algorithms (CARAMBA), 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 Algorithms, Computation, Image and Geometry (LORIA - ALGO), 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), Geometry Processing and Constrained Optimization (M2DisCo), 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-Université Lumière - Lyon 2 (UL2), This research was conducted with the support of the FEDER program of 2014-2020, the region council of Auvergne-Rhône-Alpes, the GDR-IA, and the ANR (DeCrypt ANR-18-CE39-0007). We thank the reviewers for their comments that helped us improving the paper, Jérémie Detrey for implementing the C code that checks the completeness of the sets xorEq_l, Charles Prud’homme and Jean-Guillaume Fages for their technical support on the use of Choco, and Neng-Fa Zhou for his technical support on the use of Picat., ANR-16-IDEX-0001,CAP 20-25,CAP 20-25(2016), ANR-18-CE39-0007,DeCrypt,Langage Déclaratif pour la cryptographie symétrique(2018), Université Blaise Pascal - Clermont-Ferrand 2 (UBP)-Université d'Auvergne - Clermont-Ferrand I (UdA)-SIGMA Clermont (SIGMA Clermont)-Ecole Nationale Supérieure des Mines de St Etienne (ENSM ST-ETIENNE)-Centre National de la Recherche Scientifique (CNRS), Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), 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)-Centre National de la Recherche Scientifique (CNRS)-Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Linguistics and Language, Differential cryptanalysis, Theoretical computer science, Optimization problem, Computer science, 02 engineering and technology, Encryption, Language and Linguistics, law.invention, Constraint Programming, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-CR]Computer Science [cs]/Cryptography and Security [cs.CR], Artificial Intelligence, law, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Constraint programming, Block cipher, AES, business.industry, Advanced Encryption Standard, Key (cryptography), 020201 artificial intelligence & image processing, Cryptanalysis, business
Abstract

International audience; Cryptanalysis aims at testing the properties of encryption processes, and this usually implies solving hard optimization problems. In this paper, we focus on related-key differential attacks for the Advanced Encryption Standard (AES), which is the encryption standard for block ciphers. To mount these attacks, cryptanalysts need to solve the optimal related-key differential characteristic problem. Dedicated approaches do not scale well for this problem, and need weeks to solve its hardest instances. In this paper, we improve existing Constraint Programming (CP) approaches for computing optimal related-key differential characteristics: we add new constraints that detect inconsistencies sooner, and we introduce a new decomposition of the problem in two steps. These improvements allow us to compute all optimal related-key differential characteristics for AES-128, AES-192 and AES-256 in a few hours.

Published
2020
Full Text
View/download PDF

8. Deep Variational Metric Learning for Transfer of Expressivity in Multispeaker Text to Speech

Author

Vincent Colotte, Ajinkya Kulkarni, Denis Jouvet, Speech Modeling for Facilitating Oral-Based Communication (MULTISPEECH), 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), Experiments presented in this paper were carried out using the Grid5000 testbed, supported by a scientific interest group hosted by Inria and including CNRS, RENATER and several Universities as well as other organizations. (see https://www.grid5000.fr), and Grid'5000

Subjects
Computer science, Speech recognition, deep metric learning, Contrast (statistics), 020206 networking & telecommunications, Speech synthesis, 02 engineering and technology, expressivity, computer.software_genre, Speaker recognition, Autoencoder, [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], Identity (music), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Metric (mathematics), 0202 electrical engineering, electronic engineering, information engineering, variational autoencoder, 020201 artificial intelligence & image processing, Expressivity (genetics), text-to-speech, Representation (mathematics), computer
Abstract

In this paper, we propose an approach relying on multiclass N-pair loss based deep metric learning in recurrent conditional variational autoencoder (RCVAE). We used RCVAE for implementation of multispeaker expressive text-to-speech (TTS) system. The proposed approach condition text-to-speech system on speaker embeddings, and leads to clustering the latent space representation with respect to emotion. The deep metric learning helps to reduce the intra-class variance and increase the inter-class variance in latent space. Thus, we present multiclass N-pair loss to enhance the meaningful representation of the latent space. For representing the speaker, we extracted speaker embed-dings from the x-vector based speaker recognition model trained on speech data from many speakers. To predict the vocoder features, we used RCVAE for the acoustic modeling, in which the model is conditioned on the textual features as well as on the speaker embedding. We transferred the expressivity by using the mean of the latent variables for each emotion to generate expressive speech in different speaker's voices for which no expressive speech data is available. We compared the results with those of the RCVAE model without multiclass N-pair loss as baseline model. The performance measured by mean opinion score (MOS), speaker MOS, and expressive MOS shows that N-pair loss based deep metric learning significantly improves the transfer of expressivity in the target speaker's voice in synthesized speech.

Published
2020
Full Text
View/download PDF

9. Energy-efficient joint video encoding and transmission framework for WVSN

Author

Youssef Fakhri, Patrick Corlay, Driss Aboutajdine, François-Xavier Coudoux, Othmane Alaoui-Fdili, Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), Laboratoire de Recherche en Informatique et Télécommunications [Rabat] (GSCM-LRIT), University of Mohammed V, COMmunications NUMériques - IEMN (COMNUM - IEMN), Institut d’Électronique, de Microélectronique et de Nanotechnologie - Département Opto-Acousto-Électronique - UMR 8520 (IEMN-DOAE), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France)-Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France), Faculté des Sciences [Kenitra], Université Ibn Tofaïl (UIT), Université Mohammed V de Rabat [Agdal] (UM5), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), and Acknowledgements This research was supported by the excellence fellowships program of the National Center for Scientific and Technical Research (CNRST) of Morocco (G01/003) and the Franco-Moroccan cooperation program in STICs for the research project 'RECIF'. The authors would also like to thank the editorial office Christian Malan, the editor-in-chief, the guest editors as well as the anonymous reviewers for their efforts and valuable comments and suggestions that have led to improvements in this paper.

Subjects
Computer Networks and Communications, Computer science, Real-time computing, 02 engineering and technology, Video quality, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], [SPI]Engineering Sciences [physics], Packet loss, Video encoding, Region of interest, 0202 electrical engineering, electronic engineering, information engineering, Media Technology, [INFO]Computer Science [cs], Block-matching algorithm, "Energy-efficiency in WVSN", business.industry, 020206 networking & telecommunications, Scalable Video Coding, [SPI.TRON]Engineering Sciences [physics]/Electronics, "Video distortion prediction", Rate–distortion optimization, Transmission (telecommunications), Hardware and Architecture, "Cross-layer design", 020201 artificial intelligence & image processing, "Energy consumption prediction", business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Wireless sensor network, Encoder, "Energy-efficient reliable routing", Software, Computer network
Abstract

JIF=2.101; International audience; In this paper, we propose an energy-efficient joint video encoding and transmission framework for network lifetime extension, under an end-to-end video quality constraint in the Wireless Video Sensor Networks (WVSN). This framework integrates an energy-efficient and adaptive intra-only video encoding scheme based on the H.264/AVC standard, that outputs two service differentiated macroblocks categories, namely the Region Of Interest and the Background. Empirical models describing the physical behavior of the measured energies and distortions, during the video encoding and transmission phases, are derived. These models enable the video source node to dynamically adapt its video encoder's configuration in order to meet the desired quality, while extending the network lifetime. An energy-efficient and reliable multipath multi-priority routing protocol is proposed to route the encoded streams to the sink, while considering the remaining energy, the congestion level as well as the packet loss rates of the intermediate nodes. Moreover, this protocol interacts with the application layer in order to bypass congestion situations and continuously feed it with current statistics. Through extensive numerical simulations, we demonstrate that the proposed framework does not only extend the video sensor lifetime by 54%, but it also performs significant end-to-end video quality enhancement of 35% in terms of Mean Squared Error (MSE) measurement.

Published
2017
Full Text
View/download PDF

10. Expertise-based decision support for managing food quality in agri-food companies

Author

Clément Sipieter, Bernard Cuq, Jérôme Fortin, Patrice Buche, Ingénierie des Agro-polymères et Technologies Émergentes (UMR IATE), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-Institut National de la Recherche Agronomique (INRA)-Université Montpellier 2 - Sciences et Techniques (UM2)-Centre international d'études supérieures en sciences agronomiques (Montpellier SupAgro)-Université de Montpellier (UM)-Institut national d’études supérieures agronomiques de Montpellier (Montpellier SupAgro), Centre National de la Recherche Scientifique (CNRS), Graphs for Inferences on Knowledge (GRAPHIK), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), The research leading to these results has received partial fundingfrom the CASDAR Docamex Programme from the French Ministry ofAgriculture (2016–2020). It has also benefited from preliminary worksperformed during one project with the Technical Centre of Cheeses inPoligny (CTFC) and two projects with French industrial partners. Theauthors would also like to thank the CTFC, who authorized us to presentin this paper some of the knowledge provided by their technical expertsand extracted from their knowledge base., Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro), and Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Inria Sophia Antipolis - Méditerranée (CRISAM)

Subjects
0106 biological sciences, Decision support system, Knowledge management, Computer science, Interface (Java), Knowledge Acquisition and Representation, Horticulture, Decision support systems, 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO]Computer Science [cs], 2. Zero hunger, Functional specification, business.industry, Core ontology, Forestry, 04 agricultural and veterinary sciences, Computer Science Applications, Knowledge base, Conceptual graphs, Conceptual graph, 040103 agronomy & agriculture, 0401 agriculture, forestry, and fisheries, Mind map, Graph (abstract data type), business, Knowlegde extraction, Agronomy and Crop Science, 010606 plant biology & botany
Abstract

International audience; In many agri-food companies, food quality is often managed using expertise gained through experience. Overall quality enhancement may come from sharing collective expertise. In this paper, we describe the design and implementation of a complete methodology allowing an expert knowledge base to be created and used to recommend the technical action to take to maintain food quality. We present its functional specifications, defined in cooperation with several industrial partners and technical centres over the course of several projects carried out in recent years. We propose a systematic methodology for collecting the knowledge on a given food process, from the design of a questionnaire to the synthesis of the information from completed questionnaires using a mind map approach. We then propose an original core ontology for structuring knowledge as possible causal relationships between situations of interest. We describe how mind map files generated by mind map tools are automatically imported into a conceptual graph knowledge base, before being validated and finally automatically processed in a graph-based visual tool. A specific end-user interface has been designed to ensure that end-user experts in agri-food companies can use the tool in a convenient way. Finally, our approach is compared with current research.

Published
2019
Full Text
View/download PDF

11. Automatic Discovery of Families of Network Generative Processes

Author

Telmo Menezes, Camille Roth, Centre Marc Bloch (CMB), Ministère de l'Europe et des Affaires étrangères (MEAE)-Bundesministerium für Bildung und Forschung-Ministère de l'Education nationale, de l’Enseignement supérieur et de la Recherche (M.E.N.E.S.R.)-Centre National de la Recherche Scientifique (CNRS), This paper has been partially supported by the 'Algodiv'' grant (ANR-15-CE38-0001) funded by the ANR (French National Agency of Research)., ANR-12-CORD-0018,Algopol,Politique des algorithmes(2012), and ANR-15-CE38-0001,ALGODIV,Algodiv: Recommandation algorithmique et diversité des informations du web(2015)

Subjects
Computer science, Network science, Genetic Programming, Complex networks, Genetic programming, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], 01 natural sciences, [INFO.INFO-SI]Computer Science [cs]/Social and Information Networks [cs.SI], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 03 medical and health sciences, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 0103 physical sciences, Selection (linguistics), Evolutionary computations, 010306 general physics, Artificial Intelligence/Machine Learning, 030304 developmental biology, Network model, 0303 health sciences, [SHS.STAT]Humanities and Social Sciences/Methods and statistics, [SHS.SOCIO]Humanities and Social Sciences/Sociology, business.industry, Complex network, Machine Learning ML, Network formation, Computational social sciences, Artificial intelligence, Social network Analysis SNA, business, Symbolic regression, Generative grammar
Abstract

International audience; Designing plausible network models typically requires scholars to form a priori intuitions on the key drivers of network formation. Oftentimes, these intuitions are supported by the statistical estimation of a selection of network evolution processes which will form the basis of the model to be developed. Machine learning techniques have lately been introduced to assist the automatic discovery of generative models. These approaches may more broadly be described as "symbolic regression", where fundamental network dynamic functions, rather than just parameters, are evolved through genetic programming. This chapter first aims at reviewing the principles, efforts and the emerging literature in this direction, which is very much aligned with the idea of creating artificial scientists. Our contribution then aims more specifically at building upon an approach recently developed by us [Menezes & Roth, 2014] in order to demonstrate the existence of families of networks that may be described by similar generative processes. In other words, symbolic regression may be used to group networks according to their inferred genotype (in terms of generative processes) rather than their observed phenotype (in terms of statistical/topological features). Our empirical case is based on an original data set of 238 anonymized ego-centered networks of Facebook friends, further yielding insights on the formation of sociability networks.

Published
2019
Full Text
View/download PDF

12. Non-local Social Pooling for Vehicle Trajectory Prediction

Author

Itheri Yahiaoui, Kaouther Messaoud, Fawzi Nashashibi, Anne Verroust-Blondet, Robotics & Intelligent Transportation Systems (RITS), Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Centre de Recherche en Sciences et Technologies de l'Information et de la Communication - EA 3804 (CRESTIC), Université de Reims Champagne-Ardenne (URCA), Projet PIA CAMPUS (Connected Automated Mobility Platform for Urban Sustainability), and The work presented in this paper has been financially supported by PIA French project CAMPUS (Connected Automated Mobility Platform for Urban Sustainability).

Subjects
Computer science, media_common.quotation_subject, Pooling, Context (language use), 02 engineering and technology, computer.software_genre, Motion (physics), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Highway environment, Originality, 0502 economics and business, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], ComputingMilieux_MISCELLANEOUS, media_common, 050210 logistics & transportation, 05 social sciences, [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM], 020206 networking & telecommunications, Non local, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Trajectory, Data mining, Naturalistic driving, computer
Abstract

International audience; For an efficient integration of autonomous vehicles on roads, human-like reasoning and decision making in complex traffic situations are needed. One of the key factors to achieve this goal is the estimation of the future behavior of the vehicles present in the scene. In this work, we propose a new approach to predict the motion of vehicles surrounding a target vehicle in a highway environment. Our approach is based on an LSTM encoder-decoder that uses a social pooling mechanism to model the interactions between all the neighboring vehicles. The originality of our social pooling module is that it combines both local and non-local operations. The non-local multi-head attention mechanism captures the relative importance of each vehicle despite the inter-vehicle distances to the target vehicle, while the local blocks represent nearby interactions between vehicles. This paper compares the proposed approach with the state-of-the-art using two naturalistic driving datasets: Next Generation Simulation (NGSIM) and the new highD Dataset. The proposed method outperforms existing ones in terms of RMS values of prediction error, which shows the effectiveness of combining local and non-local operations in such a context.

Published
2019
Full Text
View/download PDF

13. Evaluation of QoS for a Video Stream in a 3G Mobile Network (UMTS)

Author

Khaled Merit, Mohammed Beladgham, Ahmed Bouida, Abdelmalik Taleb-Ahmed, Université Tahri Mohammed, Béchar, Institut d’Électronique, de Microélectronique et de Nanotechnologie - Département Opto-Acousto-Électronique - UMR 8520 (IEMN-DOAE), Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), COMmunications NUMériques - IEMN (COMNUM - IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), and A C K N O W L E D G M E N TThe authors would like to be grateful to the Editor and anonymous reviewers for their valuable comments and suggestions, which have improved the quality of the paper.

Subjects
"Bandwidth", Transmission delay, Computer science, Data_CODINGANDINFORMATIONTHEORY, Communications system, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], [SPI]Engineering Sciences [physics], Packet loss, "Streaming media", "3G mobile communication", Telecommunications link, "Multiaccess communication", [INFO]Computer Science [cs], business.industry, Quality of service, ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS, "Transform coding", "Downlink", [SPI.TRON]Engineering Sciences [physics]/Electronics, Cellular network, "Quality of service", business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, UMTS frequency bands, Computer network, Communication channel
Abstract

International audience; Universal Mobile Telecommunications System) is a 3 rd generation communication system that uses WCDMA access technology (Wideband Code Division Multiple Access) to obtain high data rates and ensure better quality of multimedia communications. MPEG-4 (Moving Picture Experts Group) is widely used for video transmission services on any network because of the good quality of service it provides. UMTS has several radio channels for transporting data to and from these mobile users. This article focuses on a comparative study between the DCH channel (Dedicated Transport Channel) and the HS-DSCH channel (High Speed Downlink Shared Channel) by analyzing the qualities as packet loss, bit rate, throughput, transmission delay, availability, jitter, etc. offered by each of them in order to determine the suitable video transmission

Published
2018
Full Text
View/download PDF

14. On the Performance of Sliding Window TD-LMMSE Channel Estimation for 5G Waveforms in High Mobility Scenario

Author

Marion Berbineau, Iyad Dayoub, Michel Saideh, Département Composants et Systèmes (IFSTTAR/COSYS), Institut Français des Sciences et Technologies des Transports, de l'Aménagement et des Réseaux (IFSTTAR)-Université de Lyon-PRES Université Nantes Angers Le Mans (UNAM)-PRES Université Lille Nord de France, Institut d’Électronique, de Microélectronique et de Nanotechnologie - Département Opto-Acousto-Électronique - UMR 8520 (IEMN-DOAE), Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), COMmunications NUMériques - IEMN (COMNUM - IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France), Institut National des Sciences Appliquées (INSA), This work was supported in part by the SMARTIES project within theELSAT2020 program supported by FEDER, the French State, and the Haut deFrance Region and in part by the X2RAIL-1 project from H2020 SHIF2RAILprogram. The review of this paper was coordinated by Dr. N.-D. Dao., PRES Université Lille Nord de France-PRES Université Nantes Angers Le Mans (UNAM)-Université de Lyon-Institut Français des Sciences et Technologies des Transports, de l'Aménagement et des Réseaux (IFSTTAR), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France)-Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), and Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France)

Subjects
CHANNEL ESTIMATION, Computer Networks and Communications, Orthogonal frequency-division multiplexing, Computer science, Monte Carlo method, Aerospace Engineering, 02 engineering and technology, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], TRAITEMENT DU SIGNAL, TECHNOLOGIE SANS FIL, [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], [SPI]Engineering Sciences [physics], TELECOMMUNICATION, LMMSE, Sliding window protocol, 0202 electrical engineering, electronic engineering, information engineering, Waveform, [INFO]Computer Science [cs], Time domain, Electrical and Electronic Engineering, ONDE, Computer Science::Information Theory, 020208 electrical & electronic engineering, 020206 networking & telecommunications, FBMC, Filter bank, Computer Science::Other, [SPI.TRON]Engineering Sciences [physics]/Electronics, TRANSPORT FERROVIAIRE, Modulation, Automotive Engineering, SIMULATION, Algorithm, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 5G, Communication channel
Abstract

The upcoming 5G era is considered as a critical answer to future railway communication needs. In this correspondence, we analyze the performance of sliding window time domain (TD) LMMSE channel estimation technique where a generalized development is proposed and analyzed for 5G filter bank multicarrier-offset quadratic-amplitude modulation waveform candidates. In order to enhance performance, the analytical model is extended to exploit multipaths and multiantennas correlation wherever they do exist e.g., tunnels. TD-LMMSE performance for 5G waveforms and achieved enhancements are verified by Monte Carlo simulations.

Published
2018
Full Text
View/download PDF

15. Checksum-Filtered List Decoding Applied to H.264 and H.265 Video Error Correction

Author

Patrick Corlay, Stephane Coulombe, Firouzeh Golaghazadeh, François-Xavier Coudoux, Institut d’Électronique, de Microélectronique et de Nanotechnologie - Département Opto-Acousto-Électronique - UMR 8520 (IEMN-DOAE), Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), COMmunications NUMériques - IEMN (COMNUM - IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), This work was supported by the Natural Sciences and Engineering Research Council of Canada Discovery Grant. This paper was recommended by Associate Editor Siwei Ma, Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France)-Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), and Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France)

Subjects
Computer science, Real-time computing, List decoding, 02 engineering and technology, Data_CODINGANDINFORMATIONTHEORY, Smacker video, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], "Video Transmission", [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], [SPI]Engineering Sciences [physics], "H.265", 0202 electrical engineering, electronic engineering, information engineering, Media Technology, [INFO]Computer Science [cs], Electrical and Electronic Engineering, Bitstream, Motion compensation, "List Decoding", Network packet, "Video Error Correction", 020206 networking & telecommunications, computer.file_format, Coding tree unit, Scalable Video Coding, [SPI.TRON]Engineering Sciences [physics]/Electronics, "High Efficiency Video Coding (HEVC)", "H.264", Checksum, "Checksum", 020201 artificial intelligence & image processing, Multiview Video Coding, Error detection and correction, Algorithm, computer, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

JIF=4.046; International audience; The latest video coding standards, H.264 and H.265, are highly vulnerable in error-prone networks. Reconstructed packets may exhibit significant degradation in terms of peak signal-to-noise ratio and visual quality. This paper presents a novel list-decoding approach exploiting the receiver side user datagram protocol (UDP) checksum. The proposed method identifies the possible locations of errors by analyzing the pattern of the calculated UDP checksum. This permits considerably reducing the number of candidate bitstreams in comparison to conventional list decoding approaches. When a packet composed of N bits contains a single-bit error, instead of considering N candidate bitstreams, as is the case in conventional list decoding approaches, the proposed approach considers N/32 candidate bitstreams, leading to a reduction of 97% of the number of candidates. For a two-bit error, the reduction increases to 99.6%. The method's performance is evaluated using H.264 and H.265 test model software. Our simulation results reveal that, on average, the error was corrected perfectly 80%-90% of the time (the original bitstream was recovered). In addition, the proposed approach provides, on average, a 2.79-dB gain over frame copy (FC) error concealment using the joint model and a 3.57-dB gain over our implementation of FC error concealment in the High Efficiency Video Coding test model.

Published
2018
Full Text
View/download PDF

16. Prioritized Norms in Formal Argumentation

Author

Serena Villata, Beishui Liao, Nir Oren, Leendert van der Torre, Zhejiang University, University of Aberdeen, Individual and Collective Reasoning (ICR), University of Luxembourg [Luxembourg], Web-Instrumented Man-Machine Interactions, Communities and Semantics (WIMMICS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S - SPARKS), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), Centre National de la Recherche Scientifique (CNRS), The research reported in this paper was partially supported by the Fundamental Research Funds for the Central Universities of China for the project Big Data, Reasoning and Decision Making, the National Research Fund Luxembourg (FNR) under grant INTER/MOBILITY/14/8813732 for the project FMUAT: Formal Models for Uncertain Argumentation from Text, and the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 690974 for the project MIREL: MIning and REasoning with Legal texts., and European Project: 690974,H2020 Pilier Excellent Science,H2020-MSCA-RISE-2015,MIREL(2016)

Subjects
FOS: Computer and information sciences, Logic, Computer Science - Artificial Intelligence, Big data, [SCCO.COMP]Cognitive science/Computer science, 0102 computer and information sciences, normative multiagent systems, 01 natural sciences, ComputingMethodologies_ARTIFICIALINTELLIGENCE, Theoretical Computer Science, Argumentation theory, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Arts and Humanities (miscellaneous), normative systems, media_common.cataloged_instance, European commission, European union, China, Mathematics, media_common, deontic logic, Computer science [C05] [Engineering, computing & technology], business.industry, Deontic logic, Public relations, Sciences informatiques [C05] [Ingénierie, informatique & technologie], 16. Peace & justice, TheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGES, Artificial Intelligence (cs.AI), 010201 computation theory & mathematics, Hardware and Architecture, Normative systems, business, formal argumentation, Social psychology, norms, Software
Abstract

To resolve conflicts among norms, various nonmonotonic formalisms can be used to perform prioritized normative reasoning. Meanwhile, formal argumentation provides a way to represent nonmonotonic logics. In this paper, we propose a representation of prioritized normative reasoning by argumentation. Using hierarchical abstract normative systems, we define three kinds of prioritized normative reasoning approaches, called Greedy, Reduction, and Optimization. Then, after formulating an argumentation theory for a hierarchical abstract normative system, we show that for a totally ordered hierarchical abstract normative system, Greedy and Reduction can be represented in argumentation by applying the weakest link and the last link principles respectively, and Optimization can be represented by introducing additional defeats capturing the idea that for each argument that contains a norm not belonging to the maximal obeyable set then this argument should be rejected., Accepted by the Journal of Logic and Computation on November 2nd, 2017

Published
2017
Full Text
View/download PDF

17. Bootstrapping Q-Learning for Robotics from Neuro-Evolution Results

Author

Matthieu Zimmer, Stéphane Doncieux, Architectures et modèles d'Adptation et de la cognition (AMAC), Institut des Systèmes Intelligents et de Robotique (ISIR), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), This work has been supported by the FET project DREAM, that has received funding from the European Unions Horizon 2020 research and innovation programme under grant agreement No 640891. The authors would like to thank Olivier Sigaud for his comments on a first draft of the article. The data has been numerically analysed with the free software package GNU Octave and scikit-learn. Experiments presented in this paper were carried out using the Grid’5000 testbed, supported by a scientific interest group hosted by INRIA and including CNRS, RENATER and several Universities as well as other organizations (see https://www.grid5000.fr)., and GRID5000

Subjects
Computer Science::Machine Learning, 0209 industrial biotechnology, Learning classifier system, business.industry, Computer science, Evolutionary robotics, Q-learning, Online machine learning, Multi-task learning, generation of representation during development, 02 engineering and technology, transfer learning, Robot learning, robots with development and learning skills, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 020901 industrial engineering & automation, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Reinforcement learning, 020201 artificial intelligence & image processing, Instance-based learning, Artificial intelligence, business, Software
Abstract

International audience; Reinforcement learning problems are hard to solve in a robotics context as classical algorithms rely on discrete representations of actions and states, but in robotics both are continuous. A discrete set of actions and states can be defined, but it requires an expertise that may not be available, in particular in open environments. It is proposed to define a process to make a robot build its own representation for a reinforcement learning algorithm. The principle is to first use a direct policy search in the sensori-motor space, i.e. with no predefined discrete sets of states nor actions, and then extract from the corresponding learning traces discrete actions and identify the relevant dimensions of the state to estimate the value function. Once this is done, the robot can apply reinforcement learning (1) to be more robust to new domains and, if required, (2) to learn faster than a direct policy search. This approach allows to take the best of both worlds: first learning in a continuous space to avoid the need of a specific representation, but at a price of a long learning process and a poor generalization, and then learning with an adapted representation to be faster and more robust.

Published
2017
Full Text
View/download PDF