no code implementations • 20 Jun 2023 • Maximilian Poretschkin, Anna Schmitz, Maram Akila, Linara Adilova, Daniel Becker, Armin B. Cremers, Dirk Hecker, Sebastian Houben, Michael Mock, Julia Rosenzweig, Joachim Sicking, Elena Schulz, Angelika Voss, Stefan Wrobel
Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society.
no code implementations • 2 Dec 2022 • Dorina Weichert, Alexander Kister, Sebastian Houben, Gunar Ernis, Stefan Wrobel
Fatigue strength estimation is a costly manual material characterization process in which state-of-the-art approaches follow a standardized experiment and analysis procedure.
no code implementations • 13 Jun 2022 • Nathalie Paul, Tim Wirtz, Stefan Wrobel, Alexander Kister
We propose the introduction of a so-called pool in the system which serves as a collection point for unvisited nodes.
no code implementations • 29 Apr 2022 • Joachim Sicking, Maram Akila, Jan David Schneider, Fabian Hüger, Peter Schlicht, Tim Wirtz, Stefan Wrobel
Uncertainty estimation bears the potential to make deep learning (DL) systems more reliable.
no code implementations • 22 Oct 2021 • Till Hendrik Schulz, Pascal Welke, Stefan Wrobel
The majority of popular graph kernels is based on the concept of Haussler's $\mathcal{R}$-convolution kernel and defines graph similarities in terms of mutual substructures.
no code implementations • 10 May 2021 • Eike Stadtländer, Tamás Horváth, Stefan Wrobel
Although it has been shown quite a while ago that efficient learning of weakly convex hypotheses, a parameterized relaxation of convex hypotheses, is possible for the special case of Boolean functions, the question of whether this idea can be developed into a generic paradigm has not been studied yet.
no code implementations • 20 Jan 2021 • Till Hendrik Schulz, Tamás Horváth, Pascal Welke, Stefan Wrobel
The Weisfeiler-Lehman graph kernels are among the most prevalent graph kernels due to their remarkable time complexity and predictive performance.
no code implementations • pproximateinference AABI Symposium 2021 • Joachim Sicking, Maram Akila, Maximilian Pintz, Tim Wirtz, Asja Fischer, Stefan Wrobel
One of the most commonly used approaches so far is Monte Carlo dropout, which is computationally cheap and easy to apply in practice.
1 code implementation • 23 Dec 2020 • Joachim Sicking, Maram Akila, Maximilian Pintz, Tim Wirtz, Asja Fischer, Stefan Wrobel
Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved.
no code implementations • 14 Jul 2020 • Tiansi Dong, Chengjiang Li, Christian Bauckhage, Juanzi Li, Stefan Wrobel, Armin B. Cremers
In contrast to traditional neural network, ENN can precisely represent all 24 different structures of Syllogism.
no code implementations • 13 Jan 2020 • Florian Seiffarth, Tamas Horvath, Stefan Wrobel
As a first approach to overcome this negative result, we relax the problem to maximal closed set separation, give a generic greedy algorithm solving this problem with a linear number of closure operator calls, and show that this bound is sharp.
1 code implementation • 9 Jul 2018 • Michael Kamp, Linara Adilova, Joachim Sicking, Fabian Hüger, Peter Schlicht, Tim Wirtz, Stefan Wrobel
We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources.
no code implementations • 17 Jun 2017 • Christian Bauckhage, Eduardo Brito, Kostadin Cvejoski, Cesar Ojeda, Rafet Sifa, Stefan Wrobel
Quantum computing for machine learning attracts increasing attention and recent technological developments suggest that especially adiabatic quantum computing may soon be of practical interest.
no code implementations • 4 Apr 2017 • Rajkumar Ramamurthy, Christian Bauckhage, Krisztian Buza, Stefan Wrobel
The key idea is to assume that Alice and Bob share a copy of an echo state network.