1 code implementation • 9 Oct 2021 • Berry Weinstein, Shai Fine, Yacov Hel-Or
The weight decay regularization term is widely used during training to constrain expressivity, avoid overfitting, and improve generalization.
no code implementations • 29 Sep 2021 • Berry Weinstein, Yonatan Belinkov
As language models become larger, different pruning methods have been proposed to reduce model size.
2 code implementations • 1 Jan 2021 • Elad Hoffer, Berry Weinstein, Itay Hubara, Tal Ben-Nun, Torsten Hoefler, Daniel Soudry
Although trained on images of a specific size, it is well established that CNNs can be used to evaluate a wide range of image sizes at test time, by adjusting the size of intermediate feature maps.
no code implementations • 13 Sep 2020 • Berry Weinstein, Shai Fine, Yacov Hel-Or
We derive a new margin-based regularization formulation, termed multi-margin regularization (MMR), for deep neural networks (DNNs).
1 code implementation • 16 Nov 2019 • Berry Weinstein, Shai Fine, Yacov Hel-Or
We present a selective sampling method designed to accelerate the training of deep neural networks.
2 code implementations • 12 Aug 2019 • Elad Hoffer, Berry Weinstein, Itay Hubara, Tal Ben-Nun, Torsten Hoefler, Daniel Soudry
Although trained on images of aspecific size, it is well established that CNNs can be used to evaluate a wide range of image sizes at test time, by adjusting the size of intermediate feature maps.