Resource-aware Machine Learning - 6th International Summer School (REAML'22) 12-16 September 2022, Dortmund (Germany)


TU Dortmund University
Otto-Hahn-Strasse 14
44227 Dortmund

The International Summer School on resource-aware Machine Learning brings together lectures from the research area of data analysis (Machine Learning, data mining, statistics) and embedded systems (cyber-physical systems). It aims at taking into account the constraint of limited resources of host devices used for data analysis. The lectures are held by leading experts in these domains. The Summer School is organized by the Collaborative Research Center 876 (SFB 876).

The Summer School will be offered as a hybrid event. Due to the ongoing COVID-19 pandemic, it is not guaranteed that every international participant/lecturer can visit Dortmund. The event will thus be a mixture of local and some remote lectures. All lectures will also be streamed via Zoom and Youtube to the remote audience of participants that could not travel to Germany. Lectures will be available on-demand on YouTube during the week of the Summer School. Each lecture will be accompanied by a Q&A session. There will be a dedicated space for presenting Ph.D./PostDoc research (Students’ Corner) and a hackathon featuring real-world ML tasks ("Predicting Virus-Like Particles in Liquid Samples").

A selection of course Highlights:

- Efficient federated learning
- Matrix factorizations with binary constraints - from k-means to deep learning
- The generalization mystery in deep learning
- Deep learning on FPGAs
- Understanding inverse problems
- Counterfactual Evaluation and Learning for Interactive Systems
- Machine Learning without batteries: the next frontier wireless sensors
- Randomized Bayesian inference
- A Painless Introduction to Coresets



- Katharina Morik (TU Dortmund University, Artificial Intelligence)
- Thorsten Joachims (Cornell University, Departments of Computer Science and Information Science)
- Satrajit (Sat) Chatterjee (Palo Alto, USA, former Google AI)
- Michael Kamp (RU Bochum, Institute for Artificial Intelligence in Medicine)
- Michael Schmelling (MPI Heidelberg)
- Sibylle Hess (Eindhoven University of Technology, Data Mining)
- Johannes Köster (University Hospital Essen, Genome Informatics Group)
- Wayne Luk (Imperial College London, High Performance Embedded and Distributed Systems)
- Ce Guo (Imperial College London, Departments of Computing and of Physics)
- Han Cheng Lie (University of Potsdam, Mathematics Institute)
- Andres Gomez (University of St. Gallen, Interaction- and Communication-based Systems)
- Chris Schwiegelshohn (Aarhus University, Department of Computer Science, MADALGO)
- Tim Ruhe (TU Dortmund University, Astro-particle Physics)
- Frank Weichert (TU Dortmund University, Computer graphics lab)
- Roland Hergenröder (Leibniz-Institut für Analytische Wissenschaften-ISAS, Dortmund)



    The summer school is accompanied by a hackathon about "Predicting Virus-Like Particles in Liquid Samples". Fitting the context of the COVID-19 pandemic, participants are challenged with the detection of nanoparticles such as viruses. Using a plasmon-assisted microscopy sensor that can make nanometer-sized particles visible, we provide real-world images containing virus-like signals. The participants are challenged to test their knowledge of Machine Learning and cyber-physical systems in this real-world scenario. In this hackathon, they aim to achieve the most reliable and rapid detection possible with limited resources. 

    Students’ Corner - Share and discuss your work
    The summer school will be accompanied by an exchange platform for participants, the Students' Corner, which will allow them to network and share their research. Through this, participants will have the opportunity to present their research to each other. Additionally, graduate students from CRC 876 will present the research of their projects. The student corner will take place over the Summer School week. These sessions will provide enough time to discuss and present research and projects among the participants.


    Poster Session
    embedded systems deep learning machine learning Trustworthy AI federated learning AI CPS FPGA