Resource-aware Machine Learning

Machine learning is the key technology to discover information and concepts hidden in huge amounts of data. At the same time, 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. The increased complexity needs a new class of algorithms respecting the constraints.

Course leader

João Gama, Sangkyun Lee, Jan Madsen, Peter Marwedel, Nico Piatkowski, Jörg Rahnenführer, Wolfgang Rhode, Tim Ruhe

Target group

PhD or advanced master students from computer science or related disciplines using machine learning as an application (e.g. astrophysics, biology, medicine)

Course aim

Topics of the lectures include: Mining of ubiquitous data streams, criteria for efficient model selection or dealing with energy constraints... The theoretical lessons are accompanied by exercises and practical introductions: Analysis with RapidMiner and R, massively parallel programming with CUDA.rnA Data Mining Competition lets you test your machine learning skills on real world smartphone data.