4 September 2020
Resource-aware Machine Learningonline course
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.
A selection of course topics: Deep Learning, Graph Neural Networks, Large Models on Small Devices, Power Consumption of ML, Deep generative modeling, Memory challenges in DNN...
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. Your task will be to predict robot's positions based on sensor data. The best teams will get the chance to control the robots live, based on their predictions.
Competence Center for Machine Learning Rhine-Ruhr, ML2R, and the collaborative research center SFB 876, big data - small devices.
PhD students/PostDocs with a background in machine learning. Industry practitioners working as data scientists, machine learning experts or engineers applying machine learning.
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.
EUR 0: No fee, participation is free of charge.
A student's corner will give you the chance to present your research work, be it a virtual poster, presentation about recent publications or even a live demo. During your registration you may opt-in for the event and later upload your abstract idea.