Optimization and Automated Machine Learning

Can we use Machine Learning techniques to improve Machine Learning processes themselves? Automated Machine Learning (AutoML) is about remoiving (some of) the human element from choosing ML parameters and methods. This gives rise to a difficult optimization problem where a single performance evaluation can take a long time, so fast convergence is desirable. Our group is therefore dealing with the following questions:

Members

Name       Position
Dr. Janek Thomas       PostDoc
Jakob Richter       PostDoc
Martin Binder       PhD Student
Stefan Coors       PhD Student
Florian Karl       PhD Student
Julia Moosbauer       PhD Student
Florian Pfisterer       PhD Student
Katharina Rath       PhD Student

Projects and Software