9 citations · 21 across the 13 of their papers we have counts for
5 papers · 1 filter
Pairwise Margin Maximization for Deep Neural Networks
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. Historically, this concept was borrowe…
Margin-Based Regularization and Selective Sampling in Deep Neural Networks
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). The MMR is inspired by principles that were appl…
Autoencoder Image Interpolation by Shaping the Latent Space
Alon Oring, Zohar Yakhini, Yacov Hel-Or
Autoencoders represent an effective approach for computing the underlying factors characterizing datasets of different types. The latent representation of autoencoders have been st…
Proximity Preserving Binary Code using Signed Graph-Cut
Inbal Lav, Shai Avidan, Yoram Singer +1
We introduce a binary embedding framework, called Proximity Preserving Code (PPC), which learns similarity and dissimilarity between data points to create a compact and affinity-pr…
Selective sampling for accelerating training of deep neural networks
Berry Weinstein, Shai Fine, Yacov Hel-Or
We present a selective sampling method designed to accelerate the training of deep neural networks. To this end, we introduce a novel measurement, the minimal margin score (MMS), w…