pre-agreed price. The problem of what an option is worth is usually solved using costly numerical simulation methods. We will apply Deep Learning methods to solve the Option Pricing Problem. This cutting edge technique has the advantage that, once trained, the model can simulate many scenarios at a low computational cost. Unfortunately, training is costly […]

Data is rapidly growing in most of the applications and fields. Thus, data is becoming big data as it meets the 5V model of big data: volume, velocity, variety, veracity, and value. As a result, dimensionality reduction and feature selection become mandatory to overcome ML models’ performance and explainability issues. This project looks at feature […]

We are building a machine learning algorithm to be able to better understand the unstructured clinical notes. This will help the medical coder and auditor to quickly navigate the clinical notes and locate the text that corresponding to the codes. Reduce the chance of missing labels and mis-labeling in the coding review process.

The general objective of this research project is to develop a new natural and empathic chatbot by integrating the transformer and intent-based systems. The goal is to implement a system for expressive 3D interactive characters that can move between the structure of an intent-based system with specific Question and Answer pairs and the more open-ended […]

Deep learning and artificial intelligence (AI) technologies are transforming industry by way of automation, connectivity and availability of information technologies. However, AI remains incredibly challenging and costly to implement, often requiring massive data centers and cloud computing to operate. This research seeks to develop optimization methods to create faster, smaller and more energy-efficient AI algorithms […]

Humans possess the ability to see objects as having the same color even when viewed under different illuminations. Cameras inherently lack this capability. A process called auto white balance (AWB) has to be applied by the camera to mimic this behavior of the human visual system. AWB is one of the first steps in a […]

Ce projet est en partenariat avec Hydro-Québec. Il vise à mieux comprendre l’évolution des craques sur les turbines hydroélectriques. Pour bien s’ajuster à la demande d’électricité, ces turbines ont diverses modes d’opérations. Dans ce projet, les réseaux de neurones profonds seront utilisés afin d’obtenir une fonction qui prend en entrée le mode d’opérations et donne […]

The emerging 5G technology has tremendous potential in empowering a wide range of demanding applications. However, the 5G throughput can fluctuate wildly based on several factors like handoffs, user moving speed, user moving direction with respect to the radio base station, the terrain (e.g., obstacles between the user and the radio base station), the density […]

This project will involve using statistical modeling and machine learning techniques in order to identify significant factors that exist in user interaction logs collected from a social gaming system. Next, these factors will be used to inform, implement, and test an adaptive platform for managing and improving behaviors that relate to user experience and/or user […]

Drone technologies become more robust, and easier to use across important civil sectors, such as construction and mining, with the assurance to deliver unparalleled performance and consistency in every operation. However, one of the significant challenges in integrating drones into civil applications is related to data; i.e. lack of standards for high-quality data collection, complexity […]

The partner organization Croesus aims to provide its customers with a software solution for providing a natural language explanation of fluctuations in investment returns. The proposed research project offers an artificial intelligence-based solution which would provide such an explanation by summarizing financial documents in a way that answers the user’s question. An example of such […]

La plupart des travaux actuels sur la détection des intrusions se concentre sur la détection et l’analyse des attaques. Peu de travaux ont été réalisés sur l’analyse du comportement des attaquants eux-mêmes. Ce type d’analyse, appelée attribution, est important car il permet de remonter à la source de l’attaque, caractériser l’intention et répondre adéquatement à […]