This HLRS course addresses students, data scientists, and researchers who would like to have an introduction to Machine and Deep Learning methods to solve challenging and future-oriented problems. Both Machine and Deep Learning methods and examples as well as a method for data compression will be presented. Different examples are shown via hands-on sessions on an HLRS cluster (Vulcan). However, please be aware that this course is not a sequence of beginners’-to-advanced lectures about theoretical aspects of AI.

The first part will be an introduction to basic methods in Machine Learning, including pre-processing and supervised learning using Apache Spark. The course will then move on to elements of supervised Deep Learning on real data to classify annotated images of waste in the wild. Given the deluge of information needed to power machine and deep learning methods, it is imperative to think about effective data processing strategies. Therefore, the course will conclude with an introduction to data compression using the BigWhoop library. As an efficient data reduction tool, BigWhoop can be applied to generic numerical datasets to minimize I/O bottlenecks and optimize data storage. The lectures are interleaved with many hands-on sessions using Jupyter Notebooks and scripts on HLRS systems.
In addition, a guest lecture from the IAG will show how Deep Learning can be applied to problems in computational fluid dynamics.