Cette thèse présente trois principales contributions afin d’améliorer l’état de l’art de ces approches AutoML. Elles sont divisées entre deux thèmes de recherche: l’optimisation et meta-apprentissage. La première contribution concerne un algorithme d’optimisation hybride, appelé Mosaic, qui exploite les méthodes MCTS et optimisation bayésienne pour résoudre respectivement la sélection des algorithmes et la configuration des hyperparamètres. L’évaluation, conduite à travers le benchmark OpenML 100, montre que la performance empirique de Mosaic surpasse ceux des systèmes d’AutoML de l’état de l’art (Auto-Sklearn et TPOT). La deuxième contribution introduit une architecture de réseau neuronal, appelée Dida, qui permet d’apprendre des descripte...
International audienceThe sensitivity of machine learning (ML) algorithms w.r.t. their hyper-paramet...
International audienceThe sensitivity of machine learning (ML) algorithms w.r.t. their hyper-paramet...
Les algorithmes d'inférence ou d'optimisation possèdent généralement des hyperparamètres qu'il est n...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
International audienceThis paper tackles the AutoML problem, aimed to automatically select an ML alg...
International audienceThis paper tackles the AutoML problem, aimed to automatically select an ML alg...
International audienceThis paper tackles the AutoML problem, aimed to automatically select an ML alg...
International audienceThis paper tackles the AutoML problem, aimed to automatically select an ML alg...
L'utilisation grandissante de solutions d'apprentissage automatique (recommandation de films, reconn...
International audienceThe sensitivity of machine learning (ML) algorithms w.r.t. their hyper-paramet...
International audienceThe sensitivity of machine learning (ML) algorithms w.r.t. their hyper-paramet...
Les algorithmes d'inférence ou d'optimisation possèdent généralement des hyperparamètres qu'il est n...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
This thesis proposes three main contributions to advance the state-of-the-art of AutoML approaches. ...
International audienceThis paper tackles the AutoML problem, aimed to automatically select an ML alg...
International audienceThis paper tackles the AutoML problem, aimed to automatically select an ML alg...
International audienceThis paper tackles the AutoML problem, aimed to automatically select an ML alg...
International audienceThis paper tackles the AutoML problem, aimed to automatically select an ML alg...
L'utilisation grandissante de solutions d'apprentissage automatique (recommandation de films, reconn...
International audienceThe sensitivity of machine learning (ML) algorithms w.r.t. their hyper-paramet...
International audienceThe sensitivity of machine learning (ML) algorithms w.r.t. their hyper-paramet...
Les algorithmes d'inférence ou d'optimisation possèdent généralement des hyperparamètres qu'il est n...