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 aim to automatically learn an augmenter network by using an approximate online bilevel optimization procedure. We plan to learn a augmenter network that generates a distribution of transformations that minimizes the loss on a validation set. By unfolding the gradients of the training loss, we will optimize the loss on validation with respect to the data augmentation parameters. In this way we can provide a general solution for an efficient and automatic data augmentation that is learned jointly with the training of the model.

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.

The proposed research project will improve CM Labs’ operator training simulators with animated human characters that interact and respond to the underlying physical simulation. This will relay important dynamical cues to the trainee about the safety and correctness of the procedures. Furthermore, the developed animation controllers will allow objects to be manipulated in a realistic and plausible manner, thus improving the overall quality of the training simulation.

This project aims at evaluating whether recent results in deep learning models, trained to exploit weak labels can serve to extract meaningful lesion localizations from image-level labels, either from individual scans or given a (longitudinal) sequence thereof. To this end, we will scale up existing models that have been shown to work on 2D images to a 3D context, studying labeling performance as the dataset size grows.

La consommation énergétique des bâtiments représente à elle seule près de 40% de la consommation énergétique mondiale, et plus de 30% des émissions annuelles de gaz à effet de serre. Dans cet ordre d’idée, l’optimisation du contrôle des chauffages, de la ventilation et de la climatisation (CVC) représente un enjeu majeur pour le secteur énergétique actuel. Le présent projet met en place un système de contrôle automatisé à base d’intelligence artificielle, spécialement entraîné par renforcement positif sur des données en temps réel et par rapport à l’impact de ses décisions.

Creating a non-person character (NPC) to play a game is becoming increasingly important. NPCs can be used in quality assurance to test a game before sending the game for certification. Being able to test a game in a way that mimics a human player would allow the test to be more accurate and would help in discovering design and implementation errors resulting in time and cost savings. Recent research work reported in the literature have focused on skill-based games.

The detection, segmentation, and classification of clothes in fashion images is a well-addressed issue on deep learning research. The challenge is to achieve similar results using images taken from street and in-store sites. For such images, the variety of human positions and high diversity of clothes features decreases the results compared to the former tests. This project aims to investigate which image features and deep learning models can better execute garment detection, segmentation, and classification for in-store fashion images.

Artificial intelligence (AI) has transformed our way of perceiving and interacting with technology, by providing state-of-the-art solutions for challenging problems across the tech-spectrum. The main objective of this cluster of projects is to investigate, develop, adapt, integrate and evaluate state-of-the-art machine learning (ML) techniques, which are suitable for modeling and prediction using datasets collected for complex real-world telecommunications applications. Given the applications of interest for Ericsson Inc., we will focus on ML techniques:
1.