High-temperature mineralisation: example of the Mythril Cu-Au-Mo-Agmagmatic-hydrothermal system

Metals extraction is essential to society and to Québec’s economy, and gold is one of the main economic substance that the Province in renowned for. Gold mineralization is formed by processes involving hydrothermal fluids and these processes are not fully understood. For example, the source of the fluids, copper and gold are still hotly debated, which hinders efficient and reasonable exploitation of coppergold mineralization.

Development of a data processing and machine learning pipeline using non-invasive diffuse reflectance spectroscopy eye imaging for Alzheimer disease screening

Alzheimer’s disease (AD) is a progressive neurodegenerative disease and is currently the most common cause of dementia, affecting approximately 50 million individuals worldwide. RetiSpec has developed a non-invasive, label-free retinal imager that can uniquely detect and quantify AD biomarkers – namely, signatures of A? aggregates. The combination of hyperspectral imaging and machine learning may be a quick, simple, and cost-effective method that can be used to identify AD retinal biomarkers years before the emergence of clinical symptoms.

Unsupervised Anomaly Detection in multivariate Time Series Data

The enormous amount of data generated can be exploited using state-of-the-art AI algorithms to drive business decisions. However, a significant drawback of existing approaches is that the algorithms require a considerable amount of human effort and energy to prepare and annotate the data. Recent advances in deep learning and AI propose to solve this bottleneck using a paradigm referred to as 'Unsupervised' algorithms.

Vers l’élaboration d’une plateforme collaborative de création et de partage de connaissances dans un contexte de crise sanitaire (ex. pandémie) et environnementale (ex. catastrophes naturelles) en services préhospitaliers et hospitaliers.

Notre intention est de réaliser les travaux préalables à l’élaboration d’une plateforme collaborative de création de partage et la mise en application des nouvelles connaissances générées dans un contexte de crise sanitaire et/ou environnementale mettant l’accent sur les services préhospitaliers. Ces travaux sont à la fois théoriques en répertoriant les connaissances actuelles sur l’utilisation des applications d’écriture collaborative dans un contexte de crise.

Causal Recommender Systems for Sequential Decision-Making

Recommender systems (RS) are intended to be a personalized decision support tool, where decisions can take the form of products to buy (e.g., Amazon), movies to watch (e.g., Netflix), online news to read (e.g., Google News), or even individuals to screen for a medical condition (e.g., personalized medicine). For digital users, RS play an essential role, since the available content (and hence possible actions) grows exponentially.

Lifelong reinforcement learning with autonomous inference of subtask dependencies

In this project, we propose a continual learning approach to face the problem of forward transfer in complex reinforcement learning tasks. Concretely, we propose a model that learns how to combine a series of general modules in a deep learning architecture, so that generalization emerges through the composition of those modules. This is of vital importance for Element AI to provide reusable solutions that scale with new data, without the need of learning a new model for every problem and improving the overall performance.

Application of Deep Learning techniques in stock ranking for different horizon returns

One of the approaches portfolio managers commonly use to build portfolios, is to rank the underlying assets based on the prediction for the stock returns, as well as other aspects of the portfolio such as the portfolio risk. In this project we aim to apply different deep learning techniques to the problem of stock ranking. The features we want to use to train our models are mainly derived from fundamental company data including quarterly and annual filings of the publicly traded companies.

The development of an artificial intelligence-based platform to improve thecharacterization and the identification of unstable atherosclerotic plaques

Heart attacks and strokes are the leading causes of death and disability in the world. They are caused by the rupture of dangerous fatty deposits, called plaques, that build up in the arteries of the neck and heart. The only current method to identify whether a person is at risk of having a heart attack or stroke is to measure the narrowing of the artery caused by the plaque. However, this method is insufficient and leads to misdiagnosis or inappropriate treatment allocation.

Personalized orthosis-like toolkit for biomechanical correction of foot drop

Foot drop is a common pathology, caused by the weakening or paralysis of the foot dorsal muscles, that affects ten of thousand of Quebecers and that cause the individual to be unable to completely or partially raise his foot. It is traditionally treated with orthoses. Despite their recognized clinical relevance for reducing symptoms and pain, there are equivocal studies on the biomechanical efficacy of orthotics The ultimate goal of plantar orthosis is to stop or reduce the compensatory mechanisms of the foot joints.

Technologisation de l’entraînement de boxe et contrôle de l’anxiété: mise en relation des marqueurs biologiques et psychologiques avec l’anxiété et et la charge d’entraînement

La boxe est un sport très exigeant sur les plans physique et psychologique de sorte que le boxeur doit posséder des traits de personnalité bien spécifique afin d’accéder au niveau supérieur. Bien que le caractère soit une dimension importante, le combattant aura plusieurs obstacles à confronter lors de sa carrière modifiant ainsi ces réactions à l’approche des combats. L’un des états importants pouvant nuire à la performance est celui de l’anxiété. En effet, une anxiété mal contrôlée peut nuire considérablement à la performance et à la santé de l’athlète.