Video analytics is an active fields of research, where state-of-the-art systems rely on a variety of computer vision and machine learning techniques for accurate modeling and recognition from large-scale video datasets. Person re-identification is a key problem found in numerous application areas, e.g., video surveillance, summarization, and sports analysis, and seeks to match people across […]

Image denoising is a fundamental process in most of computer vision systems, imaging systems, and photography productions. Recently, with the power of deep neural networks, image denoising has been pushed towards new boundaries. However, neural network image denoisers are constrained by the accuracy of the noise model used to train them. Training on a poor […]

Model-free Reinforcement Learning (RL) has recently demonstrated its great potential in solving difficult intelligent tasks. However, developing a successful RL model requires an extensive model tuning and tremendous training samples. Theoretical analysis of these RL methods, more specifically policy optimization methods, only stay in a simple setting where the learning happens in the policy space. […]

L’optimisation combinatoire occupe une place prépondérante dans notre société actuelle. Que ce soit la logistique, le transport ou la gestion financière, tous ses domaines se retrouvent confrontés à des problèmes pour lesquels on recherche la meilleure solution. Cependant, un grand nombre de problèmes très complexes reste encore hors de portée des méthodes d’optimisation actuelles. C’est […]

Machine learning approaches are transforming fields such as finance, healthcare, electronic commerce, social networks, and natural disaster forecasting. We propose collaborative research that develops novel methods and applications of machine learning techniques for event prediction, modeling relations between entities, and inference techniques that can impact these domains. In the context of event prediction, we will […]

The recent advances in machine learning based on deep neural networks, coupled with the availability of phenomenal storage capacity, are transforming the industrial landscape. However, these novel machine learning approaches are known to be data hungry, as they need to tune a huge number of parameters in order to perform well. As more and more […]

Compilers are large software projects consisting of many separate but common components like code generators, garbage collectors, and runtime diagnostic tools, to name but a few. Historically compiler developers have had to write each of these components from scratch. The Eclipse OMR project was created to provide generic components for use in new compilers and […]

In recent years, deep learning has led to unprecedented advances in a wide range of applications including natural language processing, reinforcement learning, and speech recognition. Despite the abundance of empirical evidence highlighting the success of neural networks, the theoretical properties of deep learning remain poorly understood and have been a subject of active investigation. One […]

Cette recherche a pour but de documenter les particularités des écosystèmes d’innovation de Montréal et Paris constitués de relations entre trois secteurs (privé, universitaire et gouvernemental), afin de comprendre le rôle du processus de légitimation culturelle, en particulier dans la production d’un discours éthique sur l’intelligence artificielle. Grâce à la collecte de témoignages provenant des […]

Ce programme de recherche vise à proposer une approche intégrée permettant aux villes de valoriser les technologies liées à la ville intelligente et aux transports intelligents, ainsi que les données collectées, dans l’optique de répondre aux besoins de déplacements des populations, d’améliorer la sécurité des citoyens et de promouvoir la mobilité intelligente et la logistique […]

Les systèmes de recommandation sont des outils qui permettent aux utilisateurs d’un système de trouver des items qui pourraient leur être d’intérêt. Ces outils permettent d’améliorer les performances marketing à travers l’amélioration de l’expérience client, et cela en limitant le temps de recherche liés à la surcharge d’information à travers une meilleure personnalisation. Les systèmes […]

The ACPS will offer high-reliability and real-time monitoring of the smart-grid infrastructure and the secure CPS will provide secure communication and authentication of the smart-grid devices and components. This results in secure and improved power transmission that can reduce infrastructure maintenance cost for the utility companies and also reduced power-theft attacks from malicious sources. Successful […]