The goal of this SFB OSCAR intensive week workshop was to provide hands-on experience in machine learning concepts and applications in physics. The iWeek was directed at Master and PhD students, as well as postdocs. After an introduction to the foundations and basic concepts of machine learning and artificial intelligence by Dr. Ameneh Sheikhan, our invited guest lecturer Prof. Florian Marquardt (Max Planck Institute for the Science of Light and FAU Erlangen) elaborated on advanced topics in Machine Learning, such as recurrent networks or reinforcement learning, and discussed application examples of machine learning in research from a physicist’s perspective. During the hands-on coding tutorials led by Dr. Julian Schmitt, participants learned to develop and optimize neural networks, for example to perform image recognition tasks. The discussed topics prepared the participants to use machine learning algorithms to boost their experimental and theoretical methods, or to make them fit for workflows frequently used in modern data science and industry. In additional scientific talks by Dr. Maximilian Prüfer (TU Vienna) and Dr. Andreas Kell (AG Köhl, Uni Bonn), concrete examples of how machine learning can be applied in fundamental physics research, e.g., to optimize quantum gas experiments, were presented.
The event took place from 28 August – 1 September 2023 at the Bethe Center for Theoretical Physics (bctp) in Bonn. The workshop was very well received by the 37 participants.
Specific topics:
- Neural networks, gradient descent, backpropagation, autoencoders, ...
- Hands-on programming of machine learning algorithms on your computer
- Applications of machine learning in quantum physics research
Speakers:
Lecturers: Florian Marquardt (Erlangen), Ameneh Sheikhan (Bonn), Julian Schmitt (Bonn)
Scientific talks: Maximilian Prüfer (Wien), Andreas Kell (Bonn)