Electroencephalogram (EEG) Features for real-time assessment of mental state

The research project consists of looking for features that could play a role in attention and vigilance. Once this is found, the intern will have to test and implement the selected features. The trainee will have access to two datasets that are already ready. Then, she will have to analyze physiological time series. She will […]

Read More
ET.AL

Blockchain and the metaverse are emerging technologies that are capturing the attention of triple-A game studios, social media giants, and leaders in other tech domains. The metaverse can be described as a virtual 3D world, converging real world perceptions in a digital space with an infinite amount of possibilities. This convergence exactly represents the next […]

Read More
Developing the design system for a new generation of Green Fan Abradable Materials

The abradable rub strip (ARS) material’s main function is to minimize the clearance between blade tips and the fan case, thereby increasing the overall engine efficiency. Under tensile and compressive loading, the abradable material behaves different, and has a significant post-failure compaction under compressive loading. Therefore, its characterization is complex and requires a wide range […]

Read More
Active Search In the Wild

Having robots be able to conduct visual searching of objects in their environment is an important step towards building intelligent robotic assistants. Automatic object searching is a useful tool for social, service, and search and rescue robots; such robots would be required to reason about likely locations of an object specified by a user. However, […]

Read More
Bentley : Entraînement d’un détecteur de rouille par apprentissage actif

Les outils basés sur l’intelligence artificielle sont de plus en plus utilisés dans des contextes d’inspection d’infrastructures, où un expert devait normalement passer beaucoup de temps à manuellement visiter puis annoter les portions problématiques. Un problème persiste toutefois pour leur applicabilité : la quantité de supervision requise pour entraîner ces méthodes d’IA. Le projet proposé […]

Read More
Olympus NDT : Intelligence artificielle avancée pour le contrôle non destructif

L’intelligence artificielle (IA) commence à être déployée dans le domaine du contrôle non destructif. Il s’agit d’analyser, par intelligence artificielle, de grandes quantités de données, notamment ultrasonores (ce sont des échographies de matériaux métalliques, composites ou autres), pour y détecter des défauts de fabrication ou d’usure (par exemple des trous, de la corrosion, etc.). L’application […]

Read More
Analyzing User Reviews of Mobile Applicationsusing Natural Language Processing

The proposed project is to research and develop a user review analysis system for mobile games using machine learning and natural language processing techniques. Traditionally, user review analyses are done by humans, which is inefficient and relatively slow. The project will involve research in the specific areas of topic modeling, sentiment analysis and opinion spam […]

Read More
Joint burst image denoising and deblurring

Capturing high quality images is a major selling point of modern flagship smartphones. However, due to physical constraints on sensor size, capturing a good image with a mobile phone is challenging especially in low-light conditions. To obtain a bright image, one has to use a long exposure or digitally gain up a short exposure image. […]

Read More
Testing and Verification of Deep Neural Network

In AI safety, compliance ensures that a model adheres to operational specifications at runtime to avoid adverse events for the end user. This proposal looks at increasing the suite of compliance testing and verification tools available to ML practitioners by implementing two more tools, CGDTest and Goose. The overall goal is to develop both proposed […]

Read More
Globally and locally consistent molecular representations through Fibered AutoEncoders

This project aims to explore ideas from a machine learning technique called Fibered AutoEncoders (FAE) for molecular representation learning. This technique will allow us to perceive the molecular space through a topological lens using the concept of fiber bundles, and it will give us a disentangled multi-level encoding of molecules. Since the molecular space is […]

Read More
Cansbridge Fellowship

With approximately 1 million amputations performed per year worldwide, the need for prosthetics has never been more prevalent. In particular, bionic prosthetics provide more freedom and assistance to amputees as it allows them to manipulate their prosthetic with their minds, feel their surroundings, and mimic human-like movements. Unfortunately, the cost of bionic prosthetics can range […]

Read More
Exploring Educational Support Systems in Asia: How EdTech Companies are Leveraging Technology to Democratize Postsecondary Opportunities

This project will give the intern the opportunity to explore the current state of the educational support network within Asian academia, which complements the intern’s knowledge and experience on the equivalent in Canada. By analyzing the new digital resources in terms of their purposes, impact and development processes, the intern will provide the organization with […]

Read More