... | ... | @@ -22,3 +22,6 @@ Dickscheid, Timo t.dickscheid@fz-juelich.de | INM-1 Big Data Analytics Group (BD |
|
|
| Dammers, Jürgen j.dammers@fz-juelich.de | INM-4 MEG Group | A bit of supervised Deep Learning techniques (CNN and DNN) | 4D MEG data | Developing unsupervised deep learning strategies for the analysis of large sets of 4D neuroimaging data |
|
|
|
| Cavallaro, Gabriele g.cavallaro@fz-juelich.de | JSC High Productivity Data Processing Group | Supervised learning, Unsupervised learning, Feature engineering | Remote sensing data (optical and SAR) | |
|
|
|
| Axer, Markus m.axer@fz-juelich.de | INM-1 Fiber Architecture Group | none | Microscopic resolution 2D and 3D images, scalar and vector valued data |
|
|
|
| Khalid, Fahad f.khalid@fz-juelich.de | JSC SimLab Neuroscience | 1) Experience in using CNNs for image segmentation. 2) Overview of literature on distributed training and inference for deep networks. 3) Setting up and testing DL frameworks on HPC infrastructure. | 1) Very high resolution 2D images captured using the Polarized Light Imaging technology 2) Low resolution volumetric image data from Magnetic Resonance Tomography | Hardware infrastructure for training and inference, which is readily available at the JSC |
|
|
|
| Glock, Philipp p.glock@fz-juelich.de | INM-1 Big Data Analytics Group (BDA) | Deep Learning with ConvNets, Image Segmentation, pytorch, SVM | Microscopic-resolution 2D and 3D cyto images | |
|
|
|
| Comito, Claudia c.comito@fz-juelich.de | JSC - Helmholtz Analytics Framework (HAF) | Currently human-learning | | Probabilistic approach | |
|
|
\ No newline at end of file |