Search Results for author:
Found 3 papers, 2 papers with code
Robustness of Machine Learning Models Beyond Adversarial Attacks
We show that the widely used concept of adversarial robustness and closely related metrics based on counterfactuals are not necessarily valid metrics for determining the robustness of ML models against perturbations that occur "naturally", outside specific adversarial attack scenarios.
Ensemble methods for neural network-based weather forecasts
However, the skill of the neural network forecasts is systematically lower than that of state-of-the-art numerical weather prediction models.
WeatherBench: A benchmark dataset for data-driven weather forecasting
Data-driven approaches, most prominently deep learning, have become powerful tools for prediction in many domains.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
