Recommendations is one of the main ways Kobo users discover content on the platform. By using purchase history, Kobo can suggest other books similar to a certain item. However, this does not provide meaningfulrecommendations in some cases, especially for bestsellers and fiction books. Currently, only for books that have no purchase history does Kobo supply […]

The aim of this research is to investigate from traditional methods to deep learning methods, how to measure the meaning relationship between two sentences, by combining the local context, at word-level, and the global context at the sentence-level, and their ability to model informativeness and diversity of meanings expressed in natural language, i.e. in English […]

Data collection over time is a common practice in many large organizations- including financial institutions and health care providers- often with the goal of using this data to predict future challenges and opportunities. While this data may contain valuable information, it is often unstructured, coming from different sources and recorded at different times. This lack […]

Industry 4.0 is the main strategy to strengthen the competitiveness of the manufacturing sector over the next years. Simulation is a key enabling technology of Industry 4.0, supporting the development of planning and exploratory models to optimize decision making, the design and operations of complex and dynamic production systems. It may also support companies to […]

The goal of the project is to improve upon the methodology behind goal conditioned learning. In this framework, similar to the setup in traditional reinforcement learning, an agent interacts with an environment. However, instead of training the agent to maximize return, the agent is trained to reach a given goal at the end of the […]

Les pharmacies au détail s’appuient principalement sur leurs propres données empiriques pour planifier et prévoir leurs stocks. Ce type de données a ses propres caractéristiques, qui peuvent être saisonnières et être affectées par des événements spéciaux et imprévus tels que les maladies pandémiques. Toutefois, à mesure que la quantité de données s’accumule, il n’est pas […]

Machine learning has been applied in various fields and shown promising results in recent years. Researchers have found that tuning machine learning models in a proper way can vastly boost the model performance with respect to the specific AI task. However, tuning machine learning models at scale, especially finding the right hyperparameter values, can be […]

The goal of this project is to investigate fraud detection methods for micro-donation processing platforms. Fraud detection is a popular topic in both industry and academia, but usually in the context of payment processing. Through this research we aim to develop a practical, scalable and robust fraud detection system for the specific use-case of micro-donation […]

With the advancement of modern technology, especially the increase in network speed, videos are taking more and more important places among media types. With vast potential applications, video recognition has received great attention. However, video recognition is a non-trivial task: a lot of training data are needed for complicated neural networks, but annotated data are […]

By combining the information contained in the visual, audio and text content of videos, it is possible to extract complex information about their content. It’s then possible to analyse a query from a search engine to find the video segments that best matches this query. During this project, the intern will be using state-of-the-art deep […]

Bentley fournit des logiciels spécialisés et adaptés à tout type de projet d’infrastructure au niveau mondial. Le projet proposé vise à développer un détecteur d’anomalies générique basé sur un autoencodeur adversarial, qui permet l’apprentissage automatique de la distribution des éléments normaux. Par la suite, tout élément s’écartant de cette distribution peut être qualifié d’anormal, même […]

Co-operators est une coopérative canadienne, chef de file de l’assurance multiproduit et des services financiers. Co-operators cherche à explorer de nouveaux modèles d’affaires pour mieux servir sa clientèle et réussir sa mission (la sécurité financière des canadiens et canadiennes) et cela nécessite des choix stratégiques, surtout au niveau des communautés suivantes : immigrants, peuples autochtones, […]