most citedExploiting the Full Capacity of Deep Neural Networks while Avoiding Overfitting by Targeted Sparsity Regularization

3 citations · 3 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2021

The Impact of Activation Sparsity on Overfitting in Convolutional Neural Networks

Karim Huesmann, Luis Garcia Rodriguez, Lars Linsen +1

Overfitting is one of the fundamental challenges when training convolutional neural networks and is usually identified by a diverging training and test loss. The underlying dynamic…

cs.LG2020★ 3 cited

Exploiting the Full Capacity of Deep Neural Networks while Avoiding Overfitting by Targeted Sparsity Regularization

Karim Huesmann, Soeren Klemm, Lars Linsen +1

Overfitting is one of the most common problems when training deep neural networks on comparatively small datasets. Here, we demonstrate that neural network activation sparsity is a…