Pre-training large models that generalize well across the chemical space

The intern is expected to develop a pipeline for training large machine learning models on drug-like molecules to learn a broad understanding of biochemistry. This pipeline involves developing a model that can learn on many biological and quantum mechanical tasks concurrently while evaluating and improving the structure of the model using low-cost approaches from recent […]

Read More
Application of Machine Learning in Radiation Oncology Scheduling

The Ophthalmology department of CHUM receives almost 400 patients per day, each of which needs to go through different tests and consultations. Scheduling those appointments is a complicated task as it involves multiple shared resources, precedent constraints between tests, and uncertainty in tests’ durations, cancellations, emergency patients, etc. The current manual scheduling at the department […]

Read More
Sustainable Energy Production Using Biomass Gasification

Considerable growth in the global population and economy leads to an increase in fuel demand. This requires production of clean fuels with minimum CO2 emissions to maintain climate, energy, political, and social security. Hydrogen is a promising carbon-free fuel that can be produced from various renewable sources such as wind and biological systems. The microalgal […]

Read More
Dimonoff : Prédiction dynamique d’occupation d’espace de stationnement en milieu urbain

D’ici les trente prochaines années, il est anticipé que les deux tiers de la population mondiale résideront en milieu urbain. Cette statistique presse les villes à organiser leurs infrastructures dans une logique sans précédent afin de conserver ou d’améliorer la qualité de vie des citoyens. La rapidité avec laquelle la population croît et l’indisponibilité des […]

Read More
Sentiers de randonnée : Attentes et besoins des personnes en situation de handicap

Ce projet de recherche mené avec notre partenaire, l’Association Québécoise pour le Loisir des Personnes Handicapées vise à développer une classification de l’accessibilité de sentiers naturels (urbain) en partant d’indicateurs qualitatifs (motivation, attentes, besoins, satisfaction, équilibre défi-compétence, etc.) et quantitatifs (capacité fonctionnelle, force, endurance, etc.). Le présent projet se structure, d’une part, autour d’une démarche […]

Read More
Exciton-Induced Aggregation in Novel Guest Emitters for wet-coated OLEDs

The promise of low-cost fabrication via “wet” processes, such as inkjet printing, in manufacturing flat panel displays and solid-state lighting has long been one of the main motivations behind the pursuit of Organic Light-Emitting Devices (OLEDs). The vast majority of OLEDs in commercial products are still fabricated by costly “dry” vacuum-deposition methods however. A primary […]

Read More
Pitting behavior of a novel stainless steel for additive manufacturing

The last twenty years have seen whirlwind advancement in production of metallic parts via additive manufacturing (AM). This technology has surpassed its origins in manufacturing titanium parts; additive manufacturing is now applicable to a vast range of alloys, including stainless steels. The principal advantage of constructing parts layer by layer is to afford the capacity […]

Read More
Treatment of Statistical Data in the Aircraft DeicingIndustry

Every year, all planes must be deiced prior to airbourne when outside temperatures hit the cold seasons (fall to spring), in order to ensure a safe takeoff. Currently, trends in the deicing industry are still leaning towards having all operation informations logged down on paper slits. This approach is consuming in terms of time, material […]

Read More