Conference Time: 16/Dec/2019 4:47am
CET
Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
YRM4: Mathematical theory of deep learning
Time:
Monday, 18/Feb/2019:
4:30pm - 6:30pm
Session Chair: Rafael Reisenhofer Session Chair: Philipp Petersen
Location: HS 41
Presentations
4:30pm - 4:50pm Deep convolutional networks from sparse coding principles
J. Sulam 1 , A. Aberdam2 , M. Elad2
1 Johns Hopkins University, USA; 2 Technion, Israel Institute of Technology, Israel
4:50pm - 5:10pm Optimal approximation for Wilson bases with ReLU neural networks
D. Perekrestenko
ETH Zurich, Switzerland
5:10pm - 5:30pm Approximation spaces of deep neural networks
F. Voigtlaender
Catholic University of Eichstätt-Ingolstadt, Germany
5:30pm - 5:50pm Deep learning for inverse problems. Where are we, and how far can we go?
J. Adler 1,2 , O. Öktem1
1 KTH, Sweden; 2 Elekta,Sweden
5:50pm - 6:10pm Gabor frames and deep scattering networks in audio processing
R. Bammer , M. Dörfler
University of Vienna, Austria
6:10pm - 6:30pm Invertible neural networks
J. Behrmann
University Bremen, Germany
