The impressive performance of deep learning architectures is associated with a massive
increase in model complexity. Millions of parameters need to be tuned, with training and …

We study a practical yet hasn't been explored problem: how a drone can perceive in an
environment from different flight heights. Unlike autonomous driving, where the perception is …

Kernel methods are among the most flexible classes of machine learning models with strong
theoretical guarantees. Wide classes of functions can be approximated arbitrarily well with …

The ability to adapt to perceive and manipulate novel objects is an important requirement for
robots operating in unstructured dynamically-changing environments like the ones we live …

perception;● Active and self-supervised strategies for efficient learning and knowledge transfer;●
Multi-modal learning;● Reinforcement learning techniques with application to object grasping …

Non classé - Institut des sciences cognitives - UQAM Accéder à la recherche Accéder au menu
pricipal Accéder à la zone centrale UQAM Page d’accueil de l’UQAM Étudier à l’UQAM Bottin …