Deep learning models for compound design

Traditional drug development strategy is costly, tiresome, and labor-intensive. In the last decade, artificial intelligence (AI) technologies have shown promising results to overcome some of these limitations. However, these computational technologies still cannot efficiently generate novel drugs with expected properties for treating specific diseases. Here we will apply new generation of AI frameworks to design […]

Read More
Évaluation de scénarios de gestion intégrée et soutenable de l’eau dans le complexe tourbeux de Lanoraie

Le complexe tourbeux de Lanoraie fait l’objet de conflits d’usage de l’eau depuis plusieurs années et l’évolution récente de la tourbière montre une transformation très marquée de la végétation depuis 70 ans. La hausse des pompages pour l’irrigation des cultures de pommes de terre, combinée à une succession d’étés secs, a exacerbé les conflits d’usage […]

Read More
Augmentation de données et optimisation de l’espace latent d’un auto-encodeur variationnel (VAE) pour la détection de défauts et le pronostic des alternateurs hydrauliques

L’objectif du projet est d’automatiser la reconnaissance des signaux acoustiques et vibratoires d’une part, et des signaux de décharges partielles d’autres part, et ceci à l’aide d’un modèle d’apprentissage profond. Cette reconnaissance est la première étape du développement d’un modèle de pronostic et de suivi de l’évolution de la dégradation des alternateurs. Ces signaux sont […]

Read More
Portrait photo segmentation and generation with Deep Neural Network

In this project, the main purpose is to develop a tool for facial image anonymization by replacing the face in an image with a fake, generated face. To have realistic looking generated images, it is essential for the generated face to have a similar pose to the original one and to be seamlessly harmonic to […]

Read More
Object occlusion detection

Sometimes an object is partially hidden by a physical object like fingers, book etc. or by digitally pasted artifacts like blurringof an area. The intern will be working on detecting these types of digital and physical occlusions on an object. At Jumio we encounter documents that are hidden or occluded by such masks. These documents […]

Read More
Predicting acoustic and pollutant emissions from combustion equipment using experiments and machine learning

Several engineering equipment ranging from those used for portable power generation, to medium scale gas turbine aircraft engines, and large scale land-based power generation units burn fuel to produce either electric energy or generate propulsive force. This energy conversion takes place inside a combustion chamber which emits noise and combustion pollutants. The objective of the […]

Read More
Automation & Orchestration for Improved Security Communication

Speed is incredibly important when addressing issues with computer security. The longer the time between the attack’s start and resolution, the more assets that attackers can steal from a company. There are various security platforms that can alert a company to a cyber-attack. This research project aims to combine knowledge from all these platforms together […]

Read More
Automated AI-Based Phishing Solution

Phishing emails are a common form of a cyber attack. Attackers use leading content to fraud victims, such as fake banking information, forged Google Alert messages, and so on. Phishing attacks have been around for years, causing countless serious consequences, such as financial losses and confidential documents leaks. As of now, there is still no […]

Read More