L
Lars Ruthotto
Researcher at Emory University
Publications - 88
Citations - 3151
Lars Ruthotto is an academic researcher from Emory University. The author has contributed to research in topics: Artificial neural network & Inverse problem. The author has an hindex of 20, co-authored 88 publications receiving 2195 citations. Previous affiliations of Lars Ruthotto include University of Lübeck & University of Münster.
Papers
More filters
Journal ArticleDOI
Stable Architectures for Deep Neural Networks
Eldad Haber,Lars Ruthotto +1 more
TL;DR: New forward propagation techniques inspired by systems of Ordinary Differential Equations (ODE) are proposed that overcome this challenge and lead to well-posed learning problems for arbitrarily deep networks.
Journal ArticleDOI
Deep Neural Networks Motivated by Partial Differential Equations
Lars Ruthotto,Eldad Haber +1 more
TL;DR: In this article, a new PDE interpretation of a class of deep convolutional neural networks (CNN) was established, which are commonly used to learn from speech, image, and video data.
Posted Content
Reversible Architectures for Arbitrarily Deep Residual Neural Networks
TL;DR: In this article, the authors develop a theoretical framework on stability and reversibility of deep residual networks, and derive three reversible neural network architectures that can go arbitrarily deep in theory, which allows a memory-efficient implementation, which does not need to store the activations for most hidden layers.
Journal ArticleDOI
Stable Architectures for Deep Neural Networks
Eldad Haber,Lars Ruthotto +1 more
TL;DR: In this article, the authors propose new forward propagation techniques inspired by systems of Ordinary Differential Equations (ODE) that overcome the numerical instabilities in derivative-based learning algorithms commonly called exploding or vanishing gradients.
Journal ArticleDOI
hMRI – A toolbox for quantitative MRI in neuroscience and clinical research
Karsten Tabelow,Evelyne Balteau,John Ashburner,Martina F. Callaghan,Bogdan Draganski,Gunther Helms,Ferath Kherif,Tobias Leutritz,Antoine Lutti,Christophe Phillips,Enrico Reimer,Lars Ruthotto,Maryam Seif,Nikolaus Weiskopf,Gabriel Ziegler,Siawoosh Mohammadi +15 more
TL;DR: The hMRI-toolbox is introduced, an open-source, easy-to-use tool available on GitHub, for qMRI data handling and processing, and can be readily combined with existing SPM toolboxes for estimating diffusion MRI parameter maps.