A Fourier approach to Recurrent Neural Networks

Some participants have expressed interest in my recent theoretical result that relates the structure of a network to the computations that it can perform. The focus of this group/lecture will be to explain how to write down these equations that link the network structure to machine learning performance. The theoretical tools are mostly from systems engineering and statistics, and can be explained through simple-ish geometric arguments (detailed derivations can also be given for interested hardcore theorists).

Reference: Vilimelis, Yan, Liu. "Tailoring Artificial Neural Networks for Optimal Learning" https://arxiv.org/abs/1707.02469

Go to group wiki


Day Time Location
Fri, 26.04.2019 16:00 - 16:30 Panorama
Tue, 30.04.2019 15:00 - 16:00 Panorama


Pau Vilimelis Aceituno


Karla Burelo
Daniel Gutierrez-Galan
Michael Hopkins
Giacomo Indiveri
David Kappel
Sepp Kollmorgen
Mattias Nilsson
Pau Vilimelis Aceituno
Annika Weisse