Resource-aware Machine Learning - 6th International Summer School 2022

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).

TU Dortmund, Germany 12.09.2022-16.09.2022


Where

Hybrid Event: Live at TU Dortmund University & streamed Lectures.

Live Lecture Hall: TU Dortmund, Otto-Hahn-Strasse 14, Hörsaal E23
Remote Lectures: on Zoom and YouTube

Dates

Early-Bird Fee Deadline: June, 15th 2022
Begin: September, 12th 2022
End: September, 16th 2022
View more

Fees

Early-Bird Fee : 420€ (until June, 15th 2022)
Late Fee: 520€
Only streamed lectures: Free

A smartphone

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.
Lecture room

Program

Leading researchers in Machine Learning and embedded systems will give lectures on several techniques dealing with huge amounts of data, distributed data, and constraints of embedded systems.
Highlights:
Efficient federated learning From k-means to deep learning The generalization mystery in deep learning Deep learning on FPGAs Understanding inverse problems
Plasmon Assisted Microscopy of Nano-sized Objects

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.
Students' Corner

Students' Corner

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.
TU Dortmund campus

Location

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.

Lecturers
Meet our lecturers

The photo of lecturer Katharina Morik

Katharina Morik

TU Dortmund University

The photo of lecturer Michael Kamp

Michael Kamp

Ruhr-University Bochum

The photo of lecturer Michael Schmelling

Michael Schmelling

MPI Heidelberg

The photo of lecturer Sibylle Hess

Sibylle Hess

TU Eindhoven

The photo of lecturer Johannes Köster

Johannes Köster

University Hospital Essen

The photo of lecturer Satrajit (Sat) Chatterjee

Satrajit (Sat) Chatterjee

Palo Alto, CA, USA

The photo of lecturer Tim Ruhe

Tim Ruhe

TU Dortmund University

The photo of lecturer Wayne Luk

Wayne Luk

Imperial College London

The photo of lecturer Ce Guo

Ce Guo

Imperial College London

The photo of lecturer Frank Weichert

Frank Weichert

TU Dortmund University

The photo of lecturer Roland Hergenröder

Roland Hergenröder

ISAS, Dortmund

The photo of lecturer Konstantin Wüstefeld

Konstantin Wüstefeld

TU Dortmund University

The photo of lecturer Han Cheng Lie

Han Cheng Lie

University of Potsdam

The photo of lecturer Thorsten Joachims

Thorsten Joachims

Cornell University

The photo of lecturer Andres Gomez

Andres Gomez

University of St. Gallen, CH

The photo of lecturer Chris Schwiegelshohn

Chris Schwiegelshohn

Aarhus University