no code implementations • 15 Dec 2022 • Rama Cont, Alain Rossier, Renyuan Xu
We investigate the asymptotic properties of deep Residual networks (ResNets) as the number of layers increases.
no code implementations • 14 Apr 2022 • Rama Cont, Alain Rossier, Renyuan Xu
We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function.
1 code implementation • 25 May 2021 • Alain-Sam Cohen, Rama Cont, Alain Rossier, Renyuan Xu
Residual networks (ResNets) have displayed impressive results in pattern recognition and, recently, have garnered considerable theoretical interest due to a perceived link with neural ordinary differential equations (neural ODEs).