Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.
The Neural Tangent Kernel is a new way to understand the gradient descent in deep neural networks, connecting them with kernel methods. In this talk, I'll introduce this formalism and give a number of results on the Neural Tangent Kernel and explain how they give us insight into the dynamics of neural networks during training and into their generalization features.
Nicolas Henri Bernard Flammarion, Loucas Pillaud-Vivien
Martin Jaggi, Amirkeivan Mohtashami, Sebastian Urban Stich
Nicolas Henri Bernard Flammarion, Aditya Vardhan Varre, Loucas Pillaud-Vivien