direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

Machine Learning

Machine Learning is a method of data analysis that tries to identify patterns, make decisions, or more generally learn from data, in a mostly automated manner. It is a quickly growing research area and has shown quite remarkable success in various applications, for example in computer vision, medical imaging, and text & language processing.

The field of machine learning has recently gained a lot of attention with the advent of "Deep Learning" and deep neural networks. The basic concept of these deep models is not entirely new but the efficient training of deep networks has been made possible by significant advances in computational power over the last decade. In addition, the success of Deep Learning methods is fueled by the immense amount of data to learn from, which continues to grow and becomes more and more easily available.

The success of neural networks has also attracted attention from a wider audience, when trained networks defeated the worlds best players in games like Go (AlphaGo) and Chess (AlphaZero).

Machine learning is a quickly evolving and exciting research area which becomes more and more important. The majority of research in this field is empirical and often lacks a profound understanding and theoretical foundation. In many applications, for example medical imaging, it is absolutely necessary to get a better understanding of neural network predictions and their reliability. Thus, we focus our research on the mathematical and theoretical analysis of deep learning methods. 

Some of our Research Topics

Our research topics in machine learning are related to some of our other research interests, such as using deep learning methods for image processing, solving inverse problems, or solving PDEs. The research can be broadly divided into several categories: 

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions