7.1k citations
- Technical University of MunichDE23 papers
- Universität UlmDE22 papers
- University of StuttgartDE22 papers
- Technische Universität DarmstadtDE16 papers
- European Space Operations CentreDE15 papers
- Karlsruhe Institute of TechnologyDE13 papers
- University of FreiburgDE13 papers
- European Space Astronomy CentreES11 papers
- Robert Bosch (Netherlands)NL11 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- Robert Bosch (United States)US9 papers
- Technische Universität DresdenDE9 papers
12 papers · 1 filter
Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
Maximilian Stadler, Bertrand Charpentier, Simon Geisler +2
The interdependence between nodes in graphs is key to improve class predictions on nodes and utilized in approaches like Label Propagation (LP) or in Graph Neural Networks (GNN). N…
Which Minimizer Does My Neural Network Converge To?
Manuel Nonnenmacher, David Reeb, Ingo Steinwart
The loss surface of an overparameterized neural network (NN) possesses many global minima of zero training error. We explain how common variants of the standard NN training procedu…
Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang +2
Deep neural networks achieve state-of-the-art results on several tasks while increasing in complexity. It has been shown that neural networks can be pruned during training by impos…
Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
Michael Volpp, Lukas P. Fröhlich, Kirsten Fischer +4
Transferring knowledge across tasks to improve data-efficiency is one of the open key challenges in the field of global black-box optimization. Readily available algorithms are typ…
Neural Architecture Search: A Survey
Thomas Elsken, Jan Hendrik Metzen, Frank Hutter
Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect…
The streaming rollout of deep networks - towards fully model-parallel execution
Volker Fischer, Jan Köhler, Thomas Pfeil
Deep neural networks, and in particular recurrent networks, are promising candidates to control autonomous agents that interact in real-time with the physical world. However, this…