The APi project (main grant: ANR-18-CE23-0014) aims to unleash the potential of machine learning methods by addressing the fundamental issue of the pre-image from all angles in kernel methods and deep neural networks. To this end, the main objectives of the project can be summarized around the following research direction:
- Establish a new class of algorithms that overcome the curse of the pre-image, through closed-form solutions obtained using probabilistic models or joint optimization strategies.
- Implement metric learning and representation methods for time series, revisiting neural networks or kernel methods in the light of the pre-image problem.
- Explore pattern recognition on discrete structured spaces, especially for graph data, with emphasis on the task of synthesizing graphs/molecules from a set of training graphs.
- Couple the pre-imaging problem in kernel methods with two classes of neural networks, auto-encoders and generative adversarial networks (GANs), in order to provide more in-depth analyses of their underlying functioning, and to stimulate the development and exchange of ideas for designing new architectures.
- To these 4 well-identified scientific and technical objectives is added a transversal research direction that aims at exploring new application domains.
Principal investigators:
- Partenaire LITIS : Paul Honeine – http://honeine.fr
- Partenaire LTCI : Florence d’Alché – https://perso.telecom-paristech.fr/fdalche/
- Partenaire LIG : Ahlame Douzal – http://ama.liglab.fr/~douzal/