| Stable architectures for deep neural networks E Haber, L Ruthotto Inverse problems 34 (1), 014004, 2017 | 752 | 2017 |
| Deep neural networks motivated by partial differential equations L Ruthotto, E Haber Journal of Mathematical Imaging and Vision 62 (3), 352-364, 2020 | 486 | 2020 |
| Joint inversion: a structural approach E Haber, D Oldenburg Inverse problems 13 (1), 63, 1997 | 418 | 1997 |
| On optimization techniques for solving nonlinear inverse problems E Haber, UM Ascher, D Oldenburg Inverse problems 16 (5), 1263, 2000 | 404 | 2000 |
| Reversible architectures for arbitrarily deep residual neural networks B Chang, L Meng, E Haber, L Ruthotto, D Begert, E Holtham Proceedings of the AAAI conference on artificial intelligence 32 (1), 2018 | 296 | 2018 |
| Fast simulation of 3D electromagnetic problems using potentials E Haber, UM Ascher, DA Aruliah, DW Oldenburg Journal of Computational Physics 163 (1), 150-171, 2000 | 293 | 2000 |
| Intensity gradient based registration and fusion of multi-modal images E Haber, J Modersitzki Medical Image Computing and Computer-Assisted Intervention–MICCAI 2006: 9th …, 2006 | 289 | 2006 |
| Three dimensional inversion of multisource time domain electromagnetic data DW Oldenburg, E Haber, R Shekhtman Geophysics 78 (1), E47-E57, 2013 | 277 | 2013 |
| RESINVM3D: A 3D resistivity inversion package A Pidlisecky, E Haber, R Knight Geophysics 72 (2), H1-H10, 2007 | 273 | 2007 |
| Inversion of 3D electromagnetic data in frequency and time domain using an inexact all-at-once approach E Haber, UM Ascher, DW Oldenburg Geophysics 69 (5), 1216-1228, 2004 | 234 | 2004 |
| AntisymmetricRNN: A dynamical system view on recurrent neural networks B Chang, M Chen, E Haber, EH Chi arXiv preprint arXiv:1902.09689, 2019 | 226 | 2019 |
| Fast finite volume simulation of 3D electromagnetic problems with highly discontinuous coefficients E Haber, UM Ascher SIAM Journal on Scientific Computing 22 (6), 1943-1961, 2001 | 223 | 2001 |
| Numerical methods for volume preserving image registration E Haber, J Modersitzki Inverse problems 20 (5), 1621, 2004 | 210 | 2004 |
| An introduction to deep generative modeling L Ruthotto, E Haber GAMM‐Mitteilungen 44 (2), e202100008, 2021 | 209 | 2021 |
| Preconditioned all-at-once methods for large, sparse parameter estimation problems E Haber, UM Ascher Inverse Problems 17 (6), 1847, 2001 | 209 | 2001 |
| Multi-level residual networks from dynamical systems view B Chang, L Meng, E Haber, F Tung, D Begert arXiv preprint arXiv:1710.10348, 2017 | 180 | 2017 |
| Computational methods in geophysical electromagnetics E Haber Society for Industrial and Applied Mathematics, 2014 | 178 | 2014 |
| An effective method for parameter estimation with PDE constraints with multiple right-hand sides E Haber, M Chung, F Herrmann SIAM Journal on Optimization 22 (3), 739-757, 2012 | 177 | 2012 |
| A GCV based method for nonlinear ill-posed problems E Haber, D Oldenburg Computational Geosciences 4, 41-63, 2000 | 175 | 2000 |
| Intensity gradient based registration and fusion of multi-modal images E Haber, J Modersitzki Methods of information in medicine 46 (03), 292-299, 2007 | 169 | 2007 |
