For an Autonomous Vehicle (AV) to make decisions and drive independently on urban streets, the problem at hand can be broken down into many phases, two of which are perception and prediction. Perception refers to the process of extracting valuable information from the environment using data collected by sensors such as LIDAR and camera. This […]

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 […]

L’objectif de ce projet de recherche est d’améliorer la compréhension des membres par les conseillers de la Fédération des caisses Desjardins. Pour ce faire, nous avons mis en place une solution permettant d’analyser l’information provenant des appels et des discussions par chat. Grâce à différents algorithmes de traitement automatique du langage, nous pouvons extraire les […]

Dans le domaine de la gestion des infrastructures, les indicateurs de performance (IP, ou en anglais Key Performance Indicators – KPI) sont des mesures qui lient le client et le fournisseur de services. Ces indicateurs permettent de fixer des objectifs de performance que le fournisseur doit atteindre. Les IP sont particulièrement importants dans des ententes […]

The current project intends to create a software platform solution that solves the communication between organizations in the Music Industry. Overall, the platform uses third party systems to achieve the requirements of the problem statement. Moreover, the platform is built over abstraction levels to integrate different components. The research of the integration of these parties […]

Pelmorex (owner of the brands The Weather Network and MeteoMedia) operates weather information services accessed by all Canadians on desktop computers, mobile apps and television. The mobile app is one of the most downloaded and used apps in the country, within both the Apple/Google ecosystems of smart phones/tablets. Continuous and accurate location data is collected […]

Machine Learning has just started to be applied to the Legal Domain. ROSS Intelligence makes it possible for legal professionals to work faster and more effectively. Advanced Recommender Systems have not been previously applied in the Legal Domain. Yet state of the art models such as ones using Deep Collaborative Filtering have proven to be […]

Heart disease is the main reason of death worldwide. One way to understand better and detect heart diseases without need for biopsy via surgery is by using medical imaging such as magnetic resonance imaging (MRI). Cardiac magnetic resonance is a specific kind of MRI which allows great visualization of inner parts of the heart and […]

The project is about developing a decision support tool to provide a personalized handling and treatment for Autistic Syndrome Disorder patients. This decision support tool will integrate machine learning modeling that will be used to suggest optimal and personalized guidelines for a very large spectrum of ASD patients, not available so far. Theses guidelines will […]

This multidisciplinary project will investigate the social, data, and technical issues surrounding design and implementation of a blockchain-based solution for the management of consent for the use of individuals’ “omics” data in medical research. Blockchains are distributed ledgers in which confirmed and validated blocks are organized in an append-only chain using cryptographic links. This project […]

ROSS enables legal professionals by providing tools that harnesses the power of artificial intelligence to make the research process more efficient. Advances within machine learning and natural language computing enable systems to achieve close to human performance. Many state-of-the-art methods have not been applied to the legal domain, leaving opportunity to enable development for the […]

Modern robots depend on numerous hardware devices and human interaction in order to perform their task. These dependencies, in addition to the distributed nature of these systems, make automated full-system testing difficult. Current testing practices are insufficient as they only test a single component of the system or require costly manual labor. Many companies have […]