17 citations · 18 across the 2 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2022★ 1 cited
Understanding out-of-distribution accuracies through quantifying difficulty of test samples
Berfin Simsek, Melissa Hall, Levent Sagun
Existing works show that although modern neural networks achieve remarkable generalization performance on the in-distribution (ID) dataset, the accuracy drops significantly on the…
cs.LG2019★ 17 cited
Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape
Johanni Brea, Berfin Simsek, Bernd Illing +1
The permutation symmetry of neurons in each layer of a deep neural network gives rise not only to multiple equivalent global minima of the loss function, but also to first-order sa…