Summer School 2020

About

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 in a joint effort of the Competence Center for Machine Learning (ML2R) and the Collaborative Research Center 876 (SFB 876). Due to the Coronavirus pandemic the Summer School takes place as an virtual event on the internet.

Where

Online lectures on YouTube (link available soon)
Online Q&A sessions on Zoom
Student's Corner on Discord

No Fee

As the Summer School will be a virtual event, there will be no registration fee.

Important Dates

Registration Opens: 1st of June 2020
Begin: 31st of August 2020
End: 4th of September 2020

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.

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:

Interdisciplinary approaches for dealing with the constraints in cyber-physical system design Deep Learning Graph Neural Networks Large Models on Small Devices Power Consumption of ML Deep generative modeling and representation learning Memory challenges in DNN

Learn more

Hackathon

The Summer School is accompanied by a hackathon. Participants are challenged to test their knowledge of Machine Learning and cyber-physical systems in a real scenario. The logistics laboratory provides the environment for testing complex transport scenarios. A positioning system in the hall enables the precise tracking of objects, e.g. parcel robots, drones and human operators. For the Summer School, the laboratory will provide the test facility for a sensor floor, which will allow to locate objects moving on its surface without a motion tracking system. Participants will have the opportunity to apply their developed models on small device in a realistic environment. The Hackathon takes place as a Kaggle-Competition.

Learn more

Students' Corner

During the Summer School, participants will have the opportunity to present their research to each other. Additionally, researchers from ML2R and SFB 876 will present the research of their projects. The student corner will take place in dedicated online sessions over the Summer School week. These sessions will provide enough time to discuss and present research and projects among the participants. They are free to choose the format of their presentations, e.g., a poster, slides, video, or a hands-on session. 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.

Learn more

Location

Located in the heart of the urban area around the river Ruhr, the TU Dortmund University has a long history in research. 40 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 Coronavirus pandemic the Summer School has to takes place in an virtual format and cannot be held physically in Dortmund. The program will thus be available online.

Learn more