Supervision : Patrick GALLINARI
Incorporating Physical Knowledge Into Deep Neural Network
A physical process is a sustained phenomenon marked by gradual changes through a series of states occurring in the physical world. Physicists and environmental scientists attempt to model these processes in a principled way through analytic descriptions of the scientist’s prior knowledge of the underlying processes. Despite the undeniable Deep Learning success, a fully data-driven approach is not yet ready to challenge the classical approach for modeling dynamical systems.
We will try to demonstrate in this thesis that knowledge and techniques accumulated for modeling dynamical systems processes in well-developed fields such as maths or physics could be useful as a guideline to design efficient learning systems and conversely, that the ML paradigm could open new directions for modeling such complex phenomena.
We describe three tasks that are relevant to the study and modeling of Deep Learning and Dynamical System : Forecasting, hidden state discovery and unsupervised signal recovery.
Defence : 12/19/2019 - 15h - Campus Jussieu, salle 55-65/211
Jury members :
M. Étienne Mémin, INRIA Rennes, IRISA [Rapporteur]
M. François Fleuret, IDIAP, EPFL [Rapporteur]
M. Gérard Biau, Sorbonne Université, LPSM
Mme. Eniko Székely, Swiss Data Science Center
M. Nicolas Thome, CNAM, CEDRIC (Examinateur)
M. Patrick Gallinari, Sorbonne Université, LIP6
- A. Pajot : “Incorporation de connaissance physique dans des réseaux de neurones profonds”, thesis, defence 12/19/2019, supervision Gallinari, Patrick (2019)
- E. De Bézenac, A. Pajot, P. Gallinari : “Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge”, (2019)
- I. Ayed, E. De Bézenac, A. Pajot, J. Brajard, P. Gallinari : “Learning Dynamical Systems from Partial Observations”, (2019)