86 citations · 233 across the 15 of their papers we have counts for
12 papers · 1 filter
Symmetric block-low-rank layers for fully reversible multilevel neural networks
Bas Peters, Eldad Haber, Keegan Lensink
Factors that limit the size of the input and output of a neural network include memory requirements for the network states/activations to compute gradients, as well as memory for t…
Fluid Flow Mass Transport for Generative Networks
Jingrong Lin, Keegan Lensink, Eldad Haber
Generative Adversarial Networks have been shown to be powerful in generating content. To this end, they have been studied intensively in the last few years. Nonetheless, training t…
LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks
Jonathan Ephrath, Moshe Eliasof, Lars Ruthotto +2
Convolutional Neural Networks (CNNs) have become indispensable for solving machine learning tasks in speech recognition, computer vision, and other areas that involve high-dimensio…
How To Catch A Lion In The Desert -- On The Solution Of The Coverage Directed Generation (CDG) Problem
Raviv Gal, Eldad Haber, Brian Irwin +2
The testing and verification of a complex hardware or software system, such as modern integrated circuits (ICs) found in everything from smartphones to servers, can be a difficult…
LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks
Jonathan Ephrath, Lars Ruthotto, Eldad Haber +1
Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all c…
Fully Hyperbolic Convolutional Neural Networks
Keegan Lensink, Bas Peters, Eldad Haber
Convolutional Neural Networks (CNN) have recently seen tremendous success in various computer vision tasks. However, their application to problems with high dimensional input and o…