![Portrait image of Nicolas Berkouk](https://appliedmldays.org/rails/active_storage/blobs/eyJfcmFpbHMiOnsibWVzc2FnZSI6IkJBaHBBcVVGIiwiZXhwIjpudWxsLCJwdXIiOiJibG9iX2lkIn19--32abd3c62ef0882490ea18d1d5c01762e342cf8a/Screenshot%202021-03-02%20at%2010.38.39.png)
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.