The Berlin Center for Machine Learning (BZML, Berliner Zentrum für Maschinelles Lernen) aims at the systematic and sustainable expansion of interdisciplinary machine learning research, both in proven research constellations as well as in new, highly topical scientific objectives that have not yet been jointly researched.
The efficient utilization of a priori knowledge in learning processes and the investigation of the effects of erroneous or incomplete data are crucial to this mission. In parallel, BZML experts further develop techniques for interpreting and explaining complex learning methods in order to arrive at more robust and, above all, more trustworthy models. Only then can statistical models be used to solve challenging scientific problems. In particular, the requirements and statistical peculiarities from the application areas biomedicine, digital humanities and communication are central to the BZML.