The central problem of pharmaceutical research is to understand the effect of a certain molecule on human or animal biology. Many machine learning models have been developed in recent years and show great efficiency and accuracy for this kind of predictions. However, a problem common to many of the best algorithms is that they require huge amounts of data to be sure the models are well trained and make accurate predictions. This is a serious issue when such data volume is not available.

BrainBox AI is working on the mandate to provide better solutions for optimized control of HVAC systems modeled through data using AI. The Intern will continue our research at BrainBox AI and to continue to develop data driven approaches for an optimized operation of HVAC systems in design and implementation of scalable AI frameworks for AI needs in the ongoing projects at BrainBox AI. The Intern will apply AI (including ML/DL/RL), data mining and statistical approaches for the creation of scalable predictive models.

The fixed-income market consists of government and corporate bonds and other debt instruments which are used to finance operations and capital investments. The bond market remains heavily reliant on exchanges of information between counterparties and as a result information on prices is decentralized and market participants operate with different levels of information. The objective of this research project is to create improved Artificial Intelligence models which will allow market participants to better manage trading activities, manage risk, or make portfolio funding allocations.

We’d like to address the issue of 3D reconstruction from 2D images. This means developing a machine learning algorithm that can take a regular photo as an input and generate a full 3-dimensional reconstruction of the contents of the photo. Such technology can be used creatively or to help the coming generation of robots better understand their surroundings.

Dans le monde de la recherche, la majorité des algorithmes développés sont testés sur des sujets sains et jeunes. Cependant, beaucoup de projets de recherches ont pour but d’étudier des sujets ayant des pathologies. L’application des algorithmes conventionnels est donc mal adaptée à l’analyse de sujets avec pathologie. Il faut donc développer des algorithmes permettant de facilement gérer plusieurs types de pathologie. Le but de cette démarche est de faire de meilleure interprétation des analyses afin de mieux évaluer les déficits de patients.

Ce projet vise à développer une plateforme web d’évaluation de l’activité physique auprès de personne souffrant de maladies chroniques (Diabète, Maladies Cardiaques, Haute Pression Artérielle…). Elle sera facile d’utilisation et destinée aux intervenants travaillant dans les cliniques médicales. Elle exploitera les données provenant d’un capteur de pas (podomètre) et d’un questionnaire pour calculer des indicateurs statistiques. Grâce à l’intelligence artificielle, la plateforme émettra des recommandations personnalisées pour améliorer la motivation des patients à être plus actifs.

This fundamental research project investigates semantic visual navigation tasks, such as asking a household robot to “go find my keys”. We seek to enhance the efficacy of repeated search tasks within the same environment, by explicitly building, maintaining, and exploiting a map of locations that the robot had previously explored. We also seek to exploit prior location-tolocation, object-within-location, and object-to-object relationships from similar environments (e.g. within a common cultural region) to improve semantic visual navigation in unseen environments.

Optimal trade execution is a well-known problem in quantitative finance. It helps financial actors who trade large quantities of a given asset minimize their risk and their adverse price impact. The problem’s complexity is multiplied when
considering highly fragmented markets, such as those existing today for digital assets. The most recent advances in reinforcement learning and deep learning open the door to a new class of execution algorithms. This data-driven algorithm class reliefs many assumptions from the classical solutions coming from stochastic optimal control theory.

The goal of the project is to develop a predictive model that will help to make a better estimate of the relative altitude using only the barometer sensor inside the Notio device. This measurement of a precise relative altitude is crucial since it is used to compute the slope, which is an important data for the cyclist and will make the Notio even better. The difficulty of this task comes from the fact that the measurement of the altitude from the sensor has a tendency to drift and thus the computed slope also does.

In this project, we propose a continual learning approach to face the problem of catastrophic forgetting in online image classification problems. Concretely, we propose a model that learns how to mask a series of general modules in a deep learning architecture, so that generalization emerges through the composition of those modules. This is of vital importance for Element AI to provide reusable solutions that scale with new data, without the need of learning a new model for every problem and improving the overall performance.