Best thesis award for Adrian Riekert

Dr. Adrian Riekert and Prof. Dr. Gitta Kutyniok, spokesperson of the DFG-funded Priority Program 2298.
Dr. Adrian Riekert and Prof. Dr. Gitta Kutyniok, spokesperson of the DFG-funded Priority Program 2298.
© SPP2298/Christoph Bülte

Dr. Adrian Riekert, postdoc at Mathematics Münster, has been awarded the "Theoretical Foundations of Deep Learning Best Thesis Award". The award was presented by the Prof. Dr. Gitta Kutyniok, spokesperson of the DFG-funded Priority Program 2298, at the annual meeting on 12 November in Tutzing, Germany. The prize comes with 2000 Euro to be used for research purposes.

The Selection Committee outlined their reasons as follows: "What gives Riekert the edge here is the potential impact of his contributions to advance our understanding of the training problem, which is at the heart of deep learning. His excellent thesis (and numerous publications) contains a detailed analysis of training behaviors in a wide range of shallow and deep networks."

Adrian Riekert completed his dissertation "Mathematical Analysis of Gradient Methods in the Training of Artificial Neural Networks" at the Cluster of Excellence Mathematics Münster, supervised by Prof. Dr. Arnulf Jentzen. Afterwards he started a postdoc position in Jentzen's group.

Links:
SPP 2298 "Theoretical Foundations of Deep Learning"
Dr. Adrian Riekert

Talk on "Convergence in gradient methods in the training of neural networks" by Adrian Riekert at the annual meeting in Tutzing.
© SPP2298/Christoph Bülte