Utilizing pre-trained vision models for object-centric reinforcement learning

The way humans perceive their surroundings relies heavily on some sort of decomposition of those into smaller atomized entities (objects, or parts of objects). This allows for complex reasoning and prediction capabilities which are mostly seen as mundane in humans but are still a challenge to propagate to artificial systems. My project wants to explore […]

Read More
Entraînement d’un agent conversationnel pour les procédures internes

Koïos Intelligence est à la source de l’agent conversationnel Olivo qui vise à offrir une expérience interactive, guidant l’utilisateur au travers des processus de prévente, de vente et d’après-vente pour tous les types d’assurances. Bien que l’outil soit dans un état avancé tant au niveau de la conversation écrite qu’orale, et ce aussi bien en […]

Read More
Developing Crop Consulting App

This project is to build an IOS mobile application that will allow partner’s clients to use it on their mobile device to access their farm data and receive ongoing recommendations from consultants. The project will benefit the partner organization by improving the communication between consultants and their client farmers. Currently, consultants print out their recommendations […]

Read More
Automated Analysis of Call Transcripts Using Large Language Models

Analysis of customer service call transcripts can be challenging due to high volumes of unstructured textual data. To overcome this challenge, Co-operators Insurance Group seeks to explores the application of large language models (LLMs) such as GPT3 in analyzing call transcripts to extract structured data to be used in further modelling. Specifically, the project aims […]

Read More
Developing Crop Consulting Mobile App

The main purpose of the project is finding a user preferred way of synchronization and user interaction on Android platform. The result of the experiment will help the applicant to design user friendly mobile application. As a result, the partner organization can get an android version of Croprecords.com with good user experience since the system […]

Read More
Improving Anti Money Laundering through Active learning Methods

Fighting against financial crime is a battle that humanity is losing as a whole. Money Laundering is the critical component of any criminal activity that needs to be profitable. Therefore, fighting money laundering is fighting against all crimes including terrorism, human trafficking, drugs and wildlife trafficking. The United Nations (UN) estimates 2 trillion USD is […]

Read More
Question Answering over Long Clinical Documents

In traditional claim processing system, adjusters or claim handling specialists need to read massively number of medical reports like diagnosis report, medical assessment, prescription daily for different types of decision making. Such a manual review process is time-consuming and tiring, which causes slowness in serving claimants and consequently unpleasant customer experience. In the digitalization era, […]

Read More
Développement des modèles de classification et de prédiction en utilisant les techniques d’apprentissage machine sur les paramètres physiologiques pour le triage des patients durant les situations de catastrophes (VIMY Multi-system)

Ce stage s’inscrit dans le cadre du programme de recherche, VIMY, VIMY, un multi système de soins intensifs déployable sur le terrain capable de gérer de nombreux blessés. Il repose sur une capacité d’intelligence artificielle composée principalement de capteurs, de systèmes d’acquisition de données, de systèmes interactifs automatisés et d’algorithmes qui aident au processus décisionnel. […]

Read More
RevMate: Towards an optimized review process in AAA game development

In software development, code reviewing is an essential code validation step during integration [1, 2]. When developers submit their code for review, human reviewers need to validate the changes made to source code and other artifacts (e.g., data files, artifacts created by artists). This review process can go through several iterations in which the reviewers […]

Read More
Développement d’une méthode de tokenisation du génome des cancers

Ce projet vise à transformer la prise en charge des patients atteints de cancer en combinant l’intelligence artificielle et l’analyse du génome. En utilisant des techniques avancées d’apprentissage automatisés, nous allons développer un modèle novateur de tokenisation du génome des cancers, permettant d’identifier rapidement les marqueurs génétiques associés à la maladie. En parallèle, nous allons […]

Read More
Analysis of the National Chiropractic Mental Health and Wellness Survey

The public greatly depends on a country’s health care providers to be sufficiently healthy to deliver care themselves. When the wellness of health-care workers suffers, then the health of the public at large is put in jeopardy. This project represents a ground-breaking collaboration between the Canadian Medical Association (CMA) who created a comprehensive mental health […]

Read More