Description du projet
Démocratiser l’apprentissage automatique sans oublier la dimension humaine
L’apprentissage automatique automatisé (AutoML pour «automated machine learning») repose sur la confiance et l’interactivité. Ces deux facteurs sont cruciaux pour soutenir les développeurs et les chercheurs, mais, malgré les énormes progrès accomplis ces dernières années, la démocratisation de l’apprentissage automatique via AutoML ne s’est pas encore concrétisée. Au contraire, le projet ixAutoML, financé par l’UE, a été conçu de manière à placer les utilisateurs humains au cœur de plusieurs étapes. L’équipe du projet ambitionne de réunir le meilleur de deux mondes: l’intuition et les capacités de généralisation de l’homme pour les systèmes complexes, et l’efficacité des approches d’optimisation systématique pour AutoML. Ils sont convaincus que leur AutoML interactif et explicable centré sur l’homme – ixAutoML – qui arrive à point nommé, contribuera grandement à rendre l’apprentissage automatique accessible à une base d’utilisateurs beaucoup plus vaste.
Objectif
Trust and interactivity are key factors in the future development and use of automated machine learning (AutoML), supporting developers and researchers in determining powerful task-specific machine learning pipelines, including pre-processing, predictive algorithm, their hyperparameters and--if applicable--the architecture design of deep neural networks. Although AutoML is ready for its prime time after it achieved impressive results in several machine learning (ML) applications and its efficiency improved by several orders of magnitudes in recent years, democratization of machine learning via AutoML is still not achieved. In contrast to previously purely automation-centered approaches, ixAutoML is designed with human users at its heart in several stages. First of all, the foundation of trustful use of AutoML will be based on explanations of its results and processes. Therefore, we aim for:
1. Explaining static effects of design decisions in ML pipelines optimized by state-of-the-art AutoML systems.
2. Explaining dynamic AutoML policies for temporal aspects of dynamically adapted hyperparameters while ML models are trained.
These explanations will be the base for allowing interactions, bringing the best of two worlds together: human intuition and generalization capabilities for complex systems, and efficiency of systematic optimization approaches for AutoML. Concretely, we aim for:
3. Enabling interactions between humans and AutoML by taking human's latent knowledge into account and learning when to interact.
4. Building first ixAutoML prototypes and showing its efficiency in the context of Industry 4.0.
Perfectly aligned with the EU's AI strategy and recent efforts on interpretability in the ML community, we strongly believe that this timely human-centered ixAutoML will have a substantial impact on the democratization of machine learning.
Champ scientifique
Programme(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Thème(s)
Régime de financement
ERC - Support for frontier research (ERC)Institution d’accueil
30167 Hannover
Allemagne