activity
20202025
most citedExploiting the Full Capacity of Deep Neural Networks while Avoiding Overfitting by Targeted Sparsity Regularization

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

collaborators
Showing 2021Show all

1 paper · 1 filter

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…