Machine Learning and Optimization
During the last two decades, research in machine learning has evolved from the status of promising science to industrial reality. Formalized as an optimization task under constraint or as a mathematical integration, solutions to problems now exist that were previously considered beyond reach. In this context, the disciplines of machine learning and optimization constitute a cornerstone of the conception and development of systems with the capabilities to adapt and enhance through time.
We propose innovative models to design algorithms and imagine new tasks that push the possibilities given by this incoming revolution. These will make our ambient intelligence vision a reality by bringing to life intelligent systems to supervise, enhance, secure and automate our everyday activities.
The team works across deep learning, autonomous indoor robotics, adversarial learning protocols, machine reading and optimization in large graphs. We contribute to the development of the cutting edge products of NAVER LABS and are very active in the scientific communities producing papers and being involved in conferences and workshops in a variety of ways.
Recent publications by the Machine Learning and Optimization team:
Hybrid Feature Factored System for Scoring Extracted Passage Relevance in Regulatory Filings; Denys Proux, Claude Roux, Ágnes Sándor, Julien Perez
DSMM (Data Science for Macro-Modeling with Financial and Economic Datasets) workshop, part of SIGMOD 2017, Chicago, USA, 14 - 19 May 2017
Data Science for Macro-Modeling with Financial and Economic Datasets (DSMM) Workshop / FEIII challenge, Chicago, USA, 18 May 2017
Co-construction of adaptive public policies using SmartGov; Simon Pageaud, Véronique Deslandres, Salima Hassas, Vassilissa Lehoux
ICTAI 2017 - 29th International Conference on Tools with Artificial Intelligence, Boston, USA, 06 - 08 November 2017
SmartGov : Architecture générique pour exploiter les données des villes intelligentes et co-concevoir des politiques crédibles; Simon Pageaud, Véronique Deslandres, Salima Hassas, Vassilissa Lehoux
Journées Francophones sur les Systèmes Multi-Agents, Caen, France, 03 - 07 July 2017
Dialog state tracking, a machine reading approach using Memory Networks; Gated End-to-End Memory Networks
Julien Perez, Fei Liu
Conférence sur l'Apprentissage automatique (CAp), Grenoble, France, 28 - 30 June 2017
Discrepancy-based networks for unsupervised domain adaptation: a comparative study; Gabriela Csurka, Fabien Baradel, Boris Chidlovskii, Stéphane Clinchant
ICCV workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV), Venice, Italy, 22 - 29 October 2017
Mining Smart Card Data for Travelers Mini Activities; Boris Chidlovskii
ECML 2017, Skopje, Macedonia, 19 - 23 September 2017
An Extended Framework for Marginalized Domain Adaptation; Gabriela Csurka, Boris Chidlovski, Stéphane Clinchant, Sofia Michel
What to do when the access to the source data is constraint? Gabriela Csurka, Boris Chidlovski, Stéphane Clinchant
Domain Adaptation in Computer Vision Applications, Ed: Gabriela Csurka, Springer Series Advances in Computer Vision and Pattern Recognition, DOI: 10.1007/978-3-319-58347-1_14, pp. 133-149
Agents of Change. Blog article by Julien Perez