Deep Learning Classification and model compression

Deep neural networks (DNNs) have achieved great success in many visual recognition tasks. However, existing state of the art deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and […]

Read More
Enhancing adherence to online PBC wellness programming

Online wellness programming offers a promising avenue to positively influence the mental well-being of older adults with chronic conditions in a manner that is accessible and acceptable. This project aims to build on our collaborative relationship with the Canadian PBC Society to iteratively refine an online wellness program to the unique needs of individuals with […]

Read More
Discourse Representation Framework for Consumer NLP

With the ultimate goal of enhancing Nexxt Intelligence’s market research SaaS platform, inca, this project will create a flexible framework for facilitating conversations with consumers using an agent powered by natural language processing and deep learning models. This ‘discourse representation framework’ will be capable of engaging with consumers in fluent English, and is designed to […]

Read More
Accessibility at the Vancouver Writers Fest

The Vancouver Writers Fest is one of Canada’s leading literary festivals. Accessibility challenges have been a major priority for the Festival, and meeting accessibility needs will allow it to serve and grow its audience more inclusively. This project aims to improve physical accessibility for participants at the Vancouver Writers Fest. The intern will work with […]

Read More
Mobilizing Adoption of Sustainable Solutions: Accelerating the Pace of Systemic Change through Transdisciplinary Collaboration

Humanity is dependent on a sustainable future yet fails to mobilize adoption of sustainability initiatives. If current trends continue, we may not meet the 2030 UN Sustainable Develop Goals until 2082– more than half a century late. Humanity’s insufficient response to the global lack of sustainability is a grand challenge driven by a moral imperative […]

Read More
Commercializing Revolutionary New Oyster Farming Technology; Establishing and Confirming Advantages over Standard Oyster Growth Facilities

DockPort Ltd. focuses on research, development, testing, manufacture and marketing of a patented, novel, mechanized system for suspended oyster aquaculture, called BOBR (Benefit Of Being Round). DockPort is preparing to bring BOBR and related products to market. This project partners DockPort with four oyster aquaculture farmers interested in testing the BOBR innovations, together with scientific […]

Read More
Machine learning enhancements for lunar exploration

The industrial partner, Mission Control Space Services (MCSS), is a participant in an upcoming mission to launch a rover to the moon. In this project, Western students will assist MCSS by developing algorithms using techniques from deep learning to support the lunar mission. The interns will have two primary responsibilities. One intern will develop a […]

Read More
Data Drift Detection and Monitoring

When a previously trained machine learning model is put into production, the production phase begins where said model makes predictions on the inputs provided to it. When the distribution of production data changes over time, we talk about data drift. Then the model is likely to become less efficient, or even obsolete. The project consists […]

Read More
Développement d’une méthode non-supervisée d’apprentissage profond pour la détection de défaillance à partir de signaux acoustiques et vibratoires

L’objectif du projet est d’automatiser la reconnaissance des signaux acoustiques et vibratoires a l’aide d’un modele d’apprentissage profond. Cette reconnaissance est la premiere etape du developpement d’un modele de pronostic et de suivi de !’evolution de la degradation des alternateurs. Ces signaux sont issus de mesures effectuees periodiquement sur les alternateurs durant leur fonctionnement. Les […]

Read More