Nicolas Berkouk

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 am 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.

For an overview of my research, you can have a look at my Ph.D. defense:

News

I am very glad to announce that our preprint with Raphael Reinauer and Matteo Caorsi is out. You can check it here : Persformer: A Transformer Architecture for Topological Machine Learning.

With Damien Calaque and François Petit, we are launching the Persistence, Sheaves and Homotopy Theory (PSHT) online seminar. Have a look here for more informations!

Upcoming events

  • 18th February 2022 The field of Explainable AI : designing machines to explain machines ?, COSTECH (UTC - Compiègne) Seminar.
  • 17th February 2022 Persformer: A Transformer Architecture for Topological Machine Learning, DataShape (INRIA - France) Seminar, joint with Raphael Reinauer.
  • 10th February 2022 Persformer: A Transformer Architecture for Topological Machine Learning, AlToGeLiS online Seminar, joint with Raphael Reinauer.
  • 10th February 2022 The field of Explainable AI : designing machines to explain machines ?, STS Lab (UNIL - Lausanne) Seminar.

Past events

  • August 2021 Sheaves and Homotopical Methods for Topological Data Analysis, Mini-Symposium as part of the SIAM AG21' conference, Co-organizer with François Petit.
  • July 2021 5th Conference on Geometric Science of Information, Paris, France. Talk: Algebraic Homotopy Interleaving Distance.
  • May 2021 AMLD workshop on AI and Topology, EPFL, Lausanne. Talk: Level-Sets Persistence and Sheaf Theory.
  • April 2021 Workshop on Topological Data Analysis, IMSI, Chicago, US. Talk: Ephemeral Persistence Modules and Disance Comparisons.
  • June 2020 Applied Topology Seminar, EPFL, Lausanne, Switzerland. Talk: Sheaves as Computable and Stable Desciptors of Data.
  • June 2020 AATRN Seminar, online. Talk: Sheaves as Computable and Stable Desciptors of Data, video available here.
  • June 2020 Representation Theory Seminar, Bielefeld University, Bielefeld, Germany. Talk: Derived Methods for Persistence.
  • January 2019 Applied Topology workshop, Kyoto University, Kyoto, Japan. Talk: A Derived Isometry Theorem for Constructible Sheaves Over R.
  • May 2018 Bridging Statistics and Sheaves workshop, IMA, Minneapolis, USA. Poster: A Derived Isometry Theorem for Constructible Sheaves Over R.
  • March 2018 Luxembourg University, Luxembourg. Gave a 10 hours course with Steve Oudot: Theoretical Foundations of Persistence.
  • 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.