activity
20172022
most citedAntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks

86 citations · 233 across the 15 of their papers we have counts for

collaborators
Showing 2018Show all

5 papers · 1 filter

physics.geo-ph2018

Multi-resolution neural networks for tracking seismic horizons from few training images

Bas Peters, Justin Granek, Eldad Haber

Detecting a specific horizon in seismic images is a valuable tool for geological interpretation. Because hand-picking the locations of the horizon is a time-consuming process, auto…

cs.CV2018

GlymphVIS: Visualizing Glymphatic Transport Pathways Using Regularized Optimal Transport

Rena Elkin, Saad Nadeem, Eldad Haber +4

The glymphatic system (GS) is a transit passage that facilitates brain metabolic waste removal and its dysfunction has been associated with neurodegenerative diseases such as Alzhe…

math.NA2018

Never look back - A modified EnKF method and its application to the training of neural networks without back propagation

Eldad Haber, Felix Lucka, Lars Ruthotto

In this work, we present a new derivative-free optimization method and investigate its use for training neural networks. Our method is motivated by the Ensemble Kalman Filter (EnKF…

math.OC2018

Simultaneous shot inversion for nonuniform geometries using fast data interpolation

Michelle Liu, Rajiv Kumar, Eldad Haber +1

Stochastic optimization is key to efficient inversion in PDE-constrained optimization. Using 'simultaneous shots', or random superposition of source terms, works very well in simpl…

cs.LG2018

Deep Neural Networks Motivated by Partial Differential Equations

Lars Ruthotto, Eldad Haber

Partial differential equations (PDEs) are indispensable for modeling many physical phenomena and also commonly used for solving image processing tasks. In the latter area, PDE-base…