AI and Deep Learning

The theme explores the ability of deep learning to automatically extract complex representations from heterogeneous data (images, text, signals, biological data). These representations, often in the form of embeddings, make it possible to capture abstract structures useful for analysis and prediction.

Au-delà de la performance, le thème vise à développer des modèles compréhensibles et fiables. L’interprétabilité est essentielle pour garantir la confiance des utilisateurs, en particulier dans des domaines sensibles comme la santé ou l’environnement.
Ces travaux portent également sur la robustesse des modèles face à des données bruitées, incomplètes ou biaisées.

The theme addresses both discriminative approaches (classification, detection) and generative approaches (language models, image or data generation). The rise of large language models notably opens up new perspectives for natural language processing, including in low-resource contexts.

An important focus concerns the development of more resource-efficient AI models capable of operating on constrained devices (sensors, embedded systems). This objective is crucial to ensure the accessibility and sustainability of the developed solutions.