Sites Inria

There are 51 Results with the keyword : "Machine learning"

Machine learning

With GuessWhat?!, when humans play, the computer learns the language


Locating an element in an image by asking a series of questions. That is the purpose of GuessWhat?!, an interactive game created by researchers in the Sequel project team, in collaboration with a Canadian team. More than just a simple game, it is a real technical challenge: teaching a computer to dialogue naturally starting from an image. The first - promising - results have earned the team a publication at the very prestigious CVPR, the biggest international conference in the field of computer vision.


Home > Research > News > Avec GuessWhat ?! quand l’humain joue, l’ordinateur s’initie au langage


Power transition


Tao project-team (Inria Saclay - Île-de-France) -

Metis is a,tool for simulating large-scale electric systems. By doing so, it allows to evaluate different investment strategies: is it useful or not to build a new transmission line or to invest in new wind turbine farms? More generally, Metis helps in optimizing the electric infrastructure on a European level. Metis is based on black-box optimization methods and machine learning. In collaboration with the company Artelys, Metis has been tested on real test scenario.


Home > Centre > Saclay > Innovation > RII Power transition > Demos > Metis


© Sergey Nivens -

Inria Industry Meeting

Data analytics : Unlocking Knowledge and Value from Data

12th Novembre 2014 -

On 12th November 2014, Inria, in partnership with Cap Digital, CVSTENE and SystemX, organises an "Inria Industry meeting" focused on "Data Analytics". Co-located with the IEEE Conference Vis 2014, the premier forum for advances in data visualisation which brings together researchers and practitioners from academia and industry, it will take place at the Marriott Rive-Gauche Hotel in Paris. This half-day will be filled with discussions around technology demonstrations and conferences with speakers who will share their scientific, economic and industrial vision in the domain.


Home > Centre > Saclay > Innovation > RII Data Analytics > Présentation


© INRIA Sophie Auvin - P comme Protocole

Rencontres Inria Industrie

Machine Learning with Python and Scikit-learn

Project team Parietal (Inria Saclay-Île-de-France) -

Scikit-learn is an open source machine learning library. It is used by many researchers, engineers and data scientists both for scientific and business purpose. This demonstration give an overview of the latest capabilities of Scikit-learn in combination with other tools from the Python ecosystem such as Jupyter, Matplotlib and pandas.


Home > Centre > Paris > Innovation > RII "Les données" 17-18 octobre 2017 > Demos > Apprentissage Statistique en Python avec Scikit-learn


© INRIA Sophie Auvin - L comme Langage

Rencontres Inria - Industrie

Deep Neural Networks for Computer Vision Problems

Team Lacodam (Inria Rennes-Bretagne Atlantique) -

The demo will present some computer vision applications of machine learning with deep neural networks. In particular, it will show how those networks can be used for full automatic labelling of outdoor scenes and for improving the safety of chairlifts in ski resorts.


Home > Centre > Paris > Innovation > RII "Les données" 17-18 octobre 2017 > Demos > Résolution de problèmes de vision par ordinateur par des réseaux de neurones profonds


© INRIA Sophie Auvin - A comme Algorithme

Rencontres Inria Industrie

ACQUA: Forecasting Quality of Experience

Project team Diana (Inria Sophia Antipolis - Méditerranée) -

ACQUA (Application for prediCting Quality of User Experience at Internet Access) is a stress-free application that measures the performance of Internet mobile access and predicts the Quality of Experience of Internet-based applications using preloaded data-driven models. ACQUA also serves as crowdsourcing platform for Quality of Experience and network access performance measurements.


Home > Centre > Paris > Innovation > RII "Les données" 17-18 octobre 2017 > Demos > ACQUA : l'apprentissage automatique au service de la prévision de la qualité de service



Paris Sciences et Data


Chaque édition réunit autour d’un domaine d’application un chercheur en science des données, un chercheur dont la discipline est impactée par ses récentes avancées ainsi qu’une entreprise innovante du domaine qui introduisent un débat par courtes présentations. L’événement se clôture par un cocktail de networking .

Place : Inria de Paris - 2 rue Simone IFF, 75012 Paris (salle Jacques-Louis Lions)


Home > Centre > Paris > Calendar > Paris Sciences et Data

lire la suite

CC0 / Pexels

RDV du Plateau Inria

Graphs in Machine Learning


On Thursday, November 9, from 9am to 10:30am at the Plateau Inria (EuraTechnologies) will take place a conference about graphs in machine learning. This subject is the expertise of project-team Sequel from our research center. Register.

Place : Plateau Inria, EuraTechnologies - 165 avenue de Bretagne, Lille


Home > Centre > Lille > Calendar > Graphs in Machine Learning

lire la suite