Post-doctoral researcher - EPFL's Topology and Neuroscience team
Nicolas Berkouk
I am currently a post-doctoral researcher in the Topology and Neuroscience team at EPFL, under the supervision of Kathryn Hess. I was previously funded by Innosuisse, thanks to a collaboration with the Lausanne based start-up Giotto.ai, in order to use topology to investigate explicability of deep learning. I formerly completed my Ph.D. under the supervision of Steve Oudot, entitled Persistence and Sheaves: from Theory to Applications.
In my research, I melt ideas coming from real world applications' challenges with theoretical algebraic topology, in order both to develop innovative tools for machine learning, and to tackle new questions in pure mathematics. I am also collaborating with researchers in social sciences, to study the formation of the field of Explainable AI.
For an overview of my research, you can have a look at my Ph.D. defense:
Interested in the interplay between Euler Calculus, Sheaf theory and interleaving distance ? Check my new preprint here.
The PSHT (Persistence, Sheaves and Homotopy Theory) online seminar goes on for another year! For the occasion we developed a brand new website, if you're interested, you will find all the necessary information there.
December 2022 Interactions between representation theory and topological data analysis workshop, CAS, Oslo. Persistence and the Sheaf-Function Correspondence.
November 2022 Chaire Pari Seminar (Paris - France). The field of Explainable AI : designing machines to explain machines ?
February 2018 Linking Topology to Algebraic Geometry and Statistics workshop, MPI, Leipzig, Germany. Poster: Computing the convolution distance for constructible sheaves over R.
December 2017 Journées de Géométrie Algorithmique, Aussois, France. Talk: Stable resolutions of multi-parameter persistence modules.
August 2017 Developing abstract foundations for TDA, Banff Center, Canada. Talk: Stable resolutions of multi-parameter persistence modules , video available here.
March 2017 Persistent homology working group, IHP, Paris. Talk: Stable resolutions of multi-parameter persistence modules.