Our lab researches machine learning and its application to cheminformatics, bioinformatics, and computational sustainability. We are always interested in interesting new research areas both for applied and fundamental machine learning. Currently, we are particularly interested in reliability of machine learning models, adversarial machine learning, and bias, with applications in chemistry, epidemiology, and environmental research.
To learn more about our lab, check out our publications or read more about our research and projects.
You can join us as PhD student, Honours student, or other postgraduate student. You can also visit our lab as visiting researcher or student.
News
-
Artificial Intelligence and Freshwater Modelling
To protect our freshwater for future generations, we develop a framework enabling an understanding of how environmental factors impact our water quality and how mitigation strategies can help. Our project […]
Social
- Wickerlab likes Joerg Simon Wicker's comment
- And the paper is now available here:#^Targeted Attacks on Time Series ForecastingTime Series Forecasting (TSF) is well established in domains dealing with temporal data to predict future events yielding the basis for strategic decision-making. Previous research indicated that forecasting models are vulnerable to adversarial attacks, that is,…
- Wickerlab likes Joerg Simon Wicker's comment
- Wickerlab likes Joerg Simon Wicker's comment
- Or you can check our earlier preprint: #^Intriguing Usage of Applicability Domain: Lessons from Cheminformatics Applied to Adversarial LearningDefending machine learning models from adversarial attacks is still achallenge: none of the robust models is utterly immune to adversarial examplesto date. Different defences have been proposed; however, most of them aretailored to particular ML models and […]