VDI lecture: Quality guarantees and certification for machine learning processes - strategies of the Competence Center Machine Learning Rhine-Ruhr

The popularity of artificial intelligence (AI) in the media and politics has led to a gold-rush-like atmosphere when it comes to the use of AI techniques. Although impressive results can indeed be achieved in some areas of application, the overestimation of AI methods by the user harbors uncontrollable risks. Both the resources required and the thoroughness of validation are often not questioned outside specialist circles.

The lecture will present strategies of the Competence Center Machine Learning Rhine-Ruhr (ML2R), which aim to make the application of AI methods certifiable and transparent and thus counteract the above-mentioned problems:

1) Theoretical foundations for AI methods are created that allow us to provide guarantees for interpretability, quality, resource consumption and real-time behavior.
2) The human-oriented design of learning methods should achieve comprehensibility, traceability, validation and even certification.
3) Since in practical applications of machine learning there is often complex prior knowledge about the application, for example in the form of literature, simulations, physical equations or other formal models, it is investigated how such knowledge can be explicitly included in the learning process.

The strategies are explained on the basis of concrete research results and applications.

Dr. Nico Piatkowski is a senior scientist at the Competence Center Machine Learning Rhine-Ruhr (ML2R) at TU Dortmund University. His research focuses on probabilistic machine learning and machine learning under resource constraints.

Free admission.