no code implementations • 13 Apr 2021 • Karim Huesmann, Luis Garcia Rodriguez, Lars Linsen, Benjamin Risse
This tendency is preserved across network architectures and reguralisation strategies so that our measures can be used as a reliable indicator for overfitting while decoupling the network's generalisation capabilities from its loss-based definition.
no code implementations • 21 Feb 2020 • Karim Huesmann, Soeren Klemm, Lars Linsen, Benjamin Risse
Overfitting is one of the most common problems when training deep neural networks on comparatively small datasets.