Fine-tuning an LLM for patent drafting

The project seeks to optimize the performance of a Language Model (LLM) specifically tailored for patent drafting. Through meticulous fine-tuning, our objective is to elevate the LLM’s capabilities, thereby enhancing the efficiency and precision in the generation of patent documents.

Read More
Towards Causal Deep Learning to Model Ecosystems’ Response to Environmental Change

In ecological applications, Machine Learning (ML) predictions are used to make predictions about alternative scenarios. Such alternative scenarios however can change the distribution of features that the ML model relies on for predictions. The implication is that such uses-cases implicitly expect the ML model to generalize outside of the observational distribution. Unfortunately, this is often […]

Read More
Brain Assistive Tool to Predict Emotional Regulation Failures in Older Adults

The way we regulate our emotions has important implications for our well-being and our social relationships. Emotional regulation involves monitoring and controlling the intensity of one’s affective response to an external event and/or internal thought process. The impairment of emotional regulation then affects the person’s wellbeing; it also impairs the ability of the family members […]

Read More
Développement d’un pipeline de recherche documentaire ciblée

La montée en puissance de l’intelligence artificielle générative permet de construire de nouveaux produits à la fine pointe de la technologie. Dans le cadre de ce stage, un assistant virtuel capable de lire et interpréter de la documentation technique sera développé. Cette nouvelle approche permettra d’interroger une banque de document en langage naturel (autrement dit, […]

Read More
Deep learning-based quality control for tissue motion tracking in 2D-cine MRI-guided radiotherapy

With real-time acquisition of 2D imaging planes, 2D-cine MRI is often used to visualize rapidly moving tumors and organs-at-risk during radiotherapy, and automatic image registration of 2D-cine MRIs at different time points can assist in tracking tissue displacements. However, when sudden large motions occur, automatic registration algorithms can fail to track the radiation target, potentially […]

Read More
Monitoring and Interpretation of Anaerobic Digester Sensor Data

Anessa is developing software that assesses the feasibility of an anaerobic digestion facility at the earliest stages when trying to determine if a facility should be constructed. The challenge is that little information is fully known and there are a lot of factors that can affect the outcome to be positive or negative in the […]

Read More
AI in Ophthalmology triage automation

Access to specialist care, especially in rural and remote locations, is a growing challenge in Alberta. Patients with conditions such as age-related macular degeneration, diabetes, and macular edema must travel to large urban centres for assessment by retinal specialist ophthalmologists. Assessment typically requires OCT imaging, which is now broadly available through optometrist offices across the […]

Read More
Using AI and ML to advance frailty detection and management

The combination of aging alongside chronic conditions such as primary biliary cholangitis leads to accelerated muscle mass loss that impacts physical function. At advanced stages, this is termed frailty. Frailty is one of the strongest predictors of poor clinical outcomes including death. In this project we will use multidimensional digital health data and artificial intelligence […]

Read More
Apprentissage automatique quantique (QML) pour la détection du cancer

Le cancer demeure un défi mondial majeur, avec 19,3 millions de nouveaux cas et 10 millions de décès en 2020. Les progrès de l’intelligence artificielle (IA) ont amélioré la détection des tumeurs. Cependant, obtenir des informations cliniquement utiles reste un défi. L’informatique quantique offre des accélérations exponentielles, notamment avec l’apprentissage automatique quantique (QML), suscitant un […]

Read More
Developing a Mental Health Access Prioritization Algorithm as an API Service

Mental illness is considered one of the most serious conditions that one can develop. If left untreated, it could result in worsening the condition of the patient and increase the difficulty of treatment. From a patient’s perspective, most of the time even if they suffer with severe and debilitating symptoms, there’s still a prolonged wait […]

Read More
LegacyX Large Language Model – Knowledge retention, sharing and mobility

In this project, we will develop a system to revolutionize how knowledge is captured, retained, shared, managed and utilized, particularly in software development and user support. Our aim is to capture essential knowledge that has accumulated by experts and is often overlooked, organizing it systematically for easy access and application by others. A key component […]

Read More