Wednesday 17 January 2018 

Speaker: Prof Martin Erdmann (RWTH Aachen University)


Title: "Deep Learning in Particle Physics Research”

Abstract: The success of deep learning in handwriting, speech and image recognition as well as competitions in the field 
of games is currently leading to rethinking in basic research. The direct transmission of deep neural networks, e.g. at 
picture-based reconstruction of events by convolutional network architectures, has been impressive. It became evident that 
deep networks extract information from the data and use it for predictions that were not immediately accessible before. 
Therefore, the interested community currently focuses on modelling particle physics into deep network architectures. This 
talk provides an introduction to deep learning methods, presents different network architectures and their applications 
in particle physics, and discusses ways to introspect network precision and causality.