Alexander Jung

Assistant Professor of Computer Science, Aalto University

Contact information My research group Publications Teaching Short CV

My Top Achievements






The overarching goal of our research is to develop a theory that allows to tell if (and how) machine learning is possible based on data arising in a particular application. Ideally, a few easily measurable quantities (such as temperature in physics) tell us how complicated machine learning systems, e.g. deep neural networks with billions of tuneable weights, will behave. A main inspiration for our ambition are the accomplishments in physics where a single number (the temperature) can tell a lot about the global behaviour of incredibly complex systems such as a lake containing billions of water molecules.

 

 


Fast Facts
Selected Publications
Talks
first.last at aalto.fi