1 code implementation • 5 Sep 2018 • Michael Hanke, Camilla Juul Hansen, Andreas Koch, Eva K. Grebel
The analytical relations employing these FRs were trained on 124 real spectra of a benchmark sample that covers a large parameter space of $T_{\rm eff}\approx$ 4000 to 6500 K, [Fe/H] $\approx$ -4. 5 to 0. 3 dex, and $\log{g}\approx$ 1 to 5 dex, which also reflects ATHOS' range of applicability.
Solar and Stellar Astrophysics
1 code implementation • NeurIPS 2016 • Umut Güçlü, Jordy Thielen, Michael Hanke, Marcel A. J. van Gerven
We developed task-optimized deep neural networks (DNNs) that achieved state-of-the-art performance in different evaluation scenarios for automatic music tagging.
Neurons and Cognition
no code implementations • 8 Jul 2013 • Yaroslav O. Halchenko, Michael Hanke, James V. Haxby, Stephen Jose Hanson, Christoph S. Herrmann
Assessing the mapping performance on unseen data allows to localize brain areas where a significant portion of the signal could be reliably reconstructed, hence the areas neural activity of which is reflected in both EEG and fMRI data.