activity
20172022
most citedIMEXnet: A Forward Stable Deep Neural Network

24 citations · 61 across the 12 of their papers we have counts for

collaborators

12 papers

cs.CV2021

Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks

Moshe Eliasof, Benjamin Bodner, Eran Treister

Graph Convolutional Networks (GCNs) are widely used in a variety of applications, and can be seen as an unstructured version of standard Convolutional Neural Networks (CNNs). As in…

cs.LG202118 cited

PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations

Moshe Eliasof, Eldad Haber, Eran Treister

Graph neural networks are increasingly becoming the go-to approach in various fields such as computer vision, computational biology and chemistry, where data are naturally explaine…

eess.IV2021

Diffraction Tomography with Helmholtz Equation: Efficient and Robust Multigrid-Based Solver

Tao Hong, Thanh-an Pham, Eran Treister +1

Diffraction tomography is a noninvasive technique that estimates the refractive indices of unknown objects and involves an inverse-scattering problem governed by the wave equation.…

cs.LG20211 cited

GradFreeBits: Gradient Free Bit Allocation for Dynamic Low Precision Neural Networks

Benjamin J. Bodner, Gil Ben Shalom, Eran Treister

Quantized neural networks (QNNs) are among the main approaches for deploying deep neural networks on low resource edge devices. Training QNNs using different levels of precision th…

q-bio.BM2021

Mimetic Neural Networks: A unified framework for Protein Design and Folding

Moshe Eliasof, Tue Boesen, Eldad Haber +2

Recent advancements in machine learning techniques for protein folding motivate better results in its inverse problem -- protein design. In this work we introduce a new graph mimet…

cs.CE2021

Full waveform inversion using extended and simultaneous sources

Sagi Buchatsky, Eran Treister

PDE-constrained optimization problems are often treated using the reduced formulation where the PDE constraints are eliminated. This approach is known to be more computationally fe…