Benoît Legat (UCLouvain)
Title : Hidden convexity in linear neural networks Abstract : Training neural networks involves minimising a loss function that is nonconvex with …
Title : Hidden convexity in linear neural networks Abstract : Training neural networks involves minimising a loss function that is nonconvex with …
Title : Mechanisms and behaviors in complex systems with group interactions Abstract : The interplay between causal mechanisms and emerging collective behaviors …
Title : The best of both worlds: when constraint programming and machine learning help each other Abstract : Constraint programming is well …
Title : The Tidal Flows in Ocean Worlds Abstract : Planet Earth is one of a handful of ocean worlds in the …
Title : BEAMM project : How do we deal with data ? Statistical matching and WGAN generation. Abstract : In the framework …
Title : ON THE CANONICAL EQUIVALENCE OF JORDAN AND EINSTEIN FRAMES Abstract : Following a seminal paper by Dicke, physics should be …
Title : Spin-orbit dynamics under parameter drift Abstract : The dynamics of an oblate satellite in a fixed elliptical orbit, with its …
Title : How to estimate the state of a nonlinear system in a linear way? Abstract : In this work, we present …
Title : Abstract : The seminar will take place in Room S08 at the Faculty of Sciences.