220 citations · 340 across the 5 of their papers we have counts for
5 papers
Predicting the outputs of finite deep neural networks trained with noisy gradients
Gadi Naveh, Oded Ben-David, Haim Sompolinsky +1
A recent line of works studied wide deep neural networks (DNNs) by approximating them as Gaussian Processes (GPs). A DNN trained with gradient flow was shown to map to a GP governe…
The role of a layer in deep neural networks: a Gaussian Process perspective
Oded Ben-David, Zohar Ringel
A fundamental question in deep learning concerns the role played by individual layers in a deep neural network (DNN) and the transferable properties of the data representations whi…
The dependence of the dry friction threshold on rupture dynamics
Oded Ben-David, Jay Fineberg
The static friction coefficient between two materials is considered to be a material constant. We present experiments demonstrating that the ratio of shear to normal force needed t…
Oscillations in Rapid Fracture
Ariel Livne, Oded Ben-David, Jay Fineberg
Experiments of pure tensile fracture in brittle gels reveal a new dynamic oscillatory instability whose onset occurs at a critical velocity, Vc = 0.87 Cs, where Cs is the shear wav…
Experimental Study of Parametric Autoresonance in Faraday Waves
Oded Ben-David, Michael Assaf, Jay Fineberg +1
The excitation of large amplitude nonlinear waves is achieved via parametric autoresonance of Faraday waves. We experimentally demonstrate that phase locking to low amplitude drivi…