11 citations · 18 across the 7 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022★ 1 cited
On the Implicit Bias Towards Minimal Depth of Deep Neural Networks
Tomer Galanti, Liane Galanti, Ido Ben-Shaul
Recent results in the literature suggest that the penultimate (second-to-last) layer representations of neural networks that are trained for classification exhibit a clustering pro…
cs.LG2022★ 2 cited
Nearest Class-Center Simplification through Intermediate Layers
Ido Ben-Shaul, Shai Dekel
Recent advances in theoretical Deep Learning have introduced geometric properties that occur during training, past the Interpolation Threshold -- where the training error reaches z…