no code implementations • 17 Dec 2020 • Ricard Durall, Avraam Chatzimichailidis, Peter Labus, Janis Keuper
This undesirable event occurs when the model can only fit a few modes of the data distribution, while ignoring the majority of them.
2 code implementations • ICLR 2020 • Yang Yang, Yaxiong Yuan, Avraam Chatzimichailidis, Ruud JG van Sloun, Lei Lei, Symeon Chatzinotas
In this paper, we consider the problem of training neural networks (NN).
1 code implementation • 26 Sep 2019 • Avraam Chatzimichailidis, Franz-Josef Pfreundt, Nicolas R. Gauger, Janis Keuper
Current training methods for deep neural networks boil down to very high dimensional and non-convex optimization problems which are usually solved by a wide range of stochastic gradient descent methods.