Supervision: Nathanaël Perraudin,Michaël Defferrard

Project type: Semester project (master)


The Fourier spectrum is often not sufficient to discriminate complex signals because it does not take into account higher-order moments. Wide Sense Stationarity is for sure not sufficient to characterize the signal as it considers only moments of order 2. The question we try to answer in this project is: Does a graph convolutional neural network stationaries data, i.e: transform then non-linearly such that they become stationary?