Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Lars Ruthotto"'
Autor:
Abigail Julian, Lars Ruthotto
Publikováno v:
Frontiers in Neuroscience, Vol 18 (2024)
Over the past decade, reversed gradient polarity (RGP) methods have become a popular approach for correcting susceptibility artifacts in echo-planar imaging (EPI). Although several post-processing tools for RGP are available, their implementations do
Externí odkaz:
https://doaj.org/article/259a972f0af34c4aae1e6753bd5c9052
Autor:
Martina F. Callaghan, Antoine Lutti, John Ashburner, Evelyne Balteau, Nadège Corbin, Bogdan Draganski, Gunther Helms, Ferath Kherif, Tobias Leutritz, Siawoosh Mohammadi, Christophe Phillips, Enrico Reimer, Lars Ruthotto, Maryam Seif, Karsten Tabelow, Gabriel Ziegler, Nikolaus Weiskopf
Publikováno v:
Data in Brief, Vol 25, Iss , Pp - (2019)
The hMRI toolbox is an open-source toolbox for the calculation of quantitative MRI parameter maps from a series of weighted imaging data, and optionally additional calibration data. The multi-parameter mapping (MPM) protocol, incorporating calibratio
Externí odkaz:
https://doaj.org/article/a1980d187cb84cd2ba82c9803e7f1ff7
Publikováno v:
IEEE Transactions on Control Systems Technology. 31:235-251
We propose a neural network approach that yields approximate solutions for high-dimensional optimal control problems and demonstrate its effectiveness using examples from multi-agent path finding. Our approach yields controls in a feedback form, wher
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e4ef7f3f984f4e813aa7d59514f0a432
https://doi.org/10.1109/tcst.2022.3172872
https://doi.org/10.1109/tcst.2022.3172872
Publikováno v:
IEEE Transactions on Computational Imaging. 6:235-247
Phase recovery from the bispectrum is a central problem in speckle interferometry which can be posed as an optimization problem minimizing a weighted nonlinear least-squares objective function. We look at two different formulations of the phase recov
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e55de3b11f5b751a779439b2e63d378a
https://doi.org/10.1109/tci.2019.2948784
https://doi.org/10.1109/tci.2019.2948784
Publikováno v:
SIAM Journal on Mathematics of Data Science. 2:1-23
Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Ma...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5f0bbee8f54e3850a7dcd0da1babaa2
https://doi.org/10.1137/19m1247620
https://doi.org/10.1137/19m1247620
Autor:
Eldad Haber, Lars Ruthotto
Publikováno v:
GAMM-Mitteilungen. 44
Deep generative models (DGM) are neural networks with many hidden layers trained to approximate complicated, high-dimensional probability distributions using a large number of samples. When trained successfully, we can use the DGMs to estimate the li
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0784fa2b3fc2b2b312d862cb42d50190
https://doi.org/10.1002/gamm.202100008
https://doi.org/10.1002/gamm.202100008
Deep neural networks (DNNs) have shown their success as high-dimensional function approximators in many applications; however, training DNNs can be challenging in general. DNN training is commonly phrased as a stochastic optimization problem whose ch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08cee15d092453288ae392ac44701854
Deep neural networks (DNNs) have achieved state-of-the-art performance across a variety of traditional machine learning tasks, e.g., speech recognition, image classification, and segmentation. The ability of DNNs to efficiently approximate high-dimen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a086eff0367d5dfabe182094365a3d22
http://arxiv.org/abs/2007.13171
http://arxiv.org/abs/2007.13171
We present PNKH-B, a projected Newton-Krylov method for iteratively solving large-scale optimization problems with bound constraints. PNKH-B is geared toward situations in which function and gradient evaluations are expensive, and the (approximate) H
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c6e872759ee4e537e753d16313e052f
http://arxiv.org/abs/2005.13639
http://arxiv.org/abs/2005.13639