Machine Learning with resource constraints
Machine Learning is the key technology to discover information and concepts hidden in huge amounts of data. At the same time, the availability of data is ever increasing. Better sensors deliver more accurate and fine-grained data, more sensors a more complete view of the scenario. While this should lead to better learning results, it comes at a cost: Resources for the learning task are limited, restricted by computational power, communication restrictions or energy constraints.
Hackathon - Predicting Virus-Like Particles in Liquid Samples
Fitting the context of the COVID-19 pandemic, the summer school is accompanied by a challenge on 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. They will receive training datasets with particles of defined sizes for training and validating their approaches. All submitted approaches are evaluated against a previously unknown dataset and ranked using a metric that considers both the predictive quality and resource efficiency of the model.
During the Summer School, participants will have the opportunity to present their research to each other. Additionally, graduate students from SFB 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. Registered Participants will get a certificate of participation for their presentation at the end of the Summer School. A committee will select the most interesting applications. Registered participants will be informed within two weeks whether their application has been accepted.
Located in the heart of the urban area around the river Ruhr, the TU Dortmund University has a long history in research. 50 years ago, the computer science faculty was founded as one of the first of its kind. The city of Dortmund managed the transition from a center of coal mining and steel milling to information technology. Due to the ongoing COVID-19 pandemic it is not guaranteed that every international participant/lecturer can visit Dortmund. The summer school is thus planned as a hybrid event with local lectures in Dortmund and streamed lectures on the internet. The local part of the summer school takes place at the TU Dortmund, Otto-Hahn-Strasse 14, Lecture Hall E23. Have a look at the location to find more details.
The banquet dinner of the REAML Summer School will take place on Wednesday evening of the week in the restaurant "Pferdestall" on the premises of the "Zeche Zollern", an old coal mine. Local lecturers and participants will have a festive and cozy dinner in a unique location in Dortmund to chat, socialize and learn to know each other better.