506 citations · 520 across the 7 of their papers we have counts for
8 papers
Establishing and Evaluating Trustworthy AI: Overview and Research Challenges
Dominik Kowald, Sebastian Scher, Viktoria Pammer-Schindler +13
Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable out…
Machine learning based stellar classification with highly sparse photometry data
Sean Enis Cody, Sebastian Scher, Iain McDonald +3
Identifying stars belonging to different classes is vital in order to build up statistical samples of different phases and pathways of stellar evolution. In the era of surveys cove…
A conceptual model for leaving the data-centric approach in machine learning
Sebastian Scher, Bernhard Geiger, Simone Kopeinik +2
For a long time, machine learning (ML) has been seen as the abstract problem of learning relationships from data independent of the surrounding settings. This has recently been cha…
Quantifying probabilistic robustness of tree-based classifiers against natural distortions
Christoph Schweimer, Sebastian Scher
The concept of trustworthy AI has gained widespread attention lately. One of the aspects relevant to trustworthy AI is robustness of ML models. In this study, we show how to probab…
Testing robustness of predictions of trained classifiers against naturally occurring perturbations
Sebastian Scher, Andreas Trügler
Correctly quantifying the robustness of machine learning models is a central aspect in judging their suitability for specific tasks, and ultimately, for generating trust in them. W…
Physics-inspired adaptions to low-parameter neural network weather forecasts systems
Sebastian Scher, Gabriele Messori
Recently, there has been a surge of research on data-driven weather forecasting systems, especially applications based on convolutional neural networks (CNNs). These are usually tr…
Ensemble methods for neural network-based weather forecasts
Sebastian Scher, Gabriele Messori
Ensemble weather forecasts enable a measure of uncertainty to be attached to each forecast, by computing the ensemble's spread. However, generating an ensemble with a good spread-e…
WeatherBench: A benchmark dataset for data-driven weather forecasting
Stephan Rasp, Peter D. Dueben, Sebastian Scher +3
Data-driven approaches, most prominently deep learning, have become powerful tools for prediction in many domains. A natural question to ask is whether data-driven methods could al…