research
∙
05/06/2021
The layer-wise L1 Loss Landscape of Neural Nets is more complex around local minima
For fixed training data and network parameters in the other layers the L...
share
research
∙
03/31/2021
Using activation histograms to bound the number of affine regions in ReLU feed-forward neural networks
Several current bounds on the maximal number of affine regions of a ReLU...
research
∙
01/17/2019
The Oracle of DLphi
We present a novel technique based on deep learning and set theory which...
research
∙
06/05/2018