544 citations
- Klaus-Robert Müller5 profiles13 · h 17
- G. Montavon6 · h 40
- O. A. von Lilienfeld6 · h 38
- B. Demir4 · h 10
- Shinichi Nakajima3 profiles4 · h 25
- W. Samek2 profiles4 · h 67
- Kai Norman Clasen3 · h 5
- Kristof T. Schütt3 · h 25
- M. Gastegger3 · h 27
- N. W. A. Gebauer3 · h 7
- S. S. P. Hessmann3 · h 4
- Stefan Chmiela3 · h 18
- Technische Universität BerlinDE37 papers
- Korea UniversityKR12 papers
- Max Planck Institute for InformaticsDE12 papers
- Fraunhofer Institute for Telecommunications, Heinrich Hertz InstituteDE5 papers
- RIKEN Center for Advanced Intelligence ProjectJP5 papers
- Brain (Germany)DE4 papers
- Deutsches Elektronen-Synchrotron DESYDE4 papers
- University of BaselCH4 papers
- Cyprus InstituteCY3 papers
- Freie Universität BerlinDE3 papers
- University of TorontoCA3 papers
- University of ViennaAT3 papers
6 papers · 1 filter
Gradient-Guided Furthest Point Sampling for Robust Training Set Selection
Morris Trestman, Stefan Gugler, Felix A. Faber +1
Training set sampling methods are used to improve model performance and lower data costs in machine learning problems relevant to chemistry. We introduce Gradient Guided Furthest P…
Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures
Florian Bley, Jacob Kauffmann, Simon León Krug +2
Distance-based classifiers, such as k-nearest neighbors and support vector machines, continue to be a workhorse of machine learning, widely used in science and industry. In practic…
Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks
Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker +5
Physics-informed neural networks (PINNs) offer a powerful approach to solving partial differential equations (PDEs), which are ubiquitous in the quantitative sciences. Applied to b…
Towards Desiderata-Driven Design of Visual Counterfactual Explainers
Sidney Bender, Jan Herrmann, Klaus-Robert Müller +1
Visual counterfactual explainers (VCEs) are a straightforward and promising approach to enhancing the transparency of image classifiers. VCEs complement other types of explanations…
On the Role of Pre-trained Embeddings in Binary Code Analysis
Alwin Maier, Felix Weissberg, Konrad Rieck
Deep learning has enabled remarkable progress in binary code analysis. In particular, pre-trained embeddings of assembly code have become a gold standard for solving analysis tasks…
Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation
Adrian Hill, Guillaume Dalle
From implicit differentiation to probabilistic modeling, Jacobian and Hessian matrices have many potential use cases in Machine Learning (ML), but they are viewed as computationall…