28 April - Course was postponed from May, 17 - 19 to June, 28 - 30 2021.
This course will be held online using Zoom.
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 will be presented, together with their implementation on HLRS systems. 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 (part of the EXCELLERAT Data Exchange and Workflow Portal). 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.
08:45 - 09:00 on every day: drop in to Zoom
Day 1: Focus on Pre-processing, Feature Engineering and Machine Learning (9:00 - 17:00 tbe, Dr.-Ing. Lorenzo Zanon)
The first day will be based on the “Stuttgart S-Bahn Example” (originally developed by Dennis Hoppe, HLRS) to provide an introduction to Machine Learning. The focus is on data preparation, classification and regression algorithms in supervised learning: Can these tools be helpful to improve the travel experience in the Stuttgart S-Bahn, which are their limits? Apache Spark will be employed for the hands-on sessions on Jupyter Notebooks as well as via interactive jobs on script. Finally, we will also touch upon the visualisation of results.
Day 2: Focus on data processing, Model of ANN and supervised Deep Learning to classify images of waste in the wild (9:00 - 17:00 tbe, Dr. Khatuna Kakhiani)
During second day, participants will explore how Deep Learning can be used to classification waste in wild. After brief introduction of Deep Learning, and basic concepts and Building blocks of Deep Neural Networks, participants will learn how to:
On the 3rd day we start with a guest lecture about Deep Neural Networks for Data-Driven Turbulence Models, using Deep Learning in Computational Fluid Dynamics. It will be given by Dr.-Ing. Andrea Beck, Institute of Aerodynamics and Gas Dynamics, University of Stuttgart. The preliminary abstract from 2020 can be found here.
We will conclude the day with an introduction to data compression, focusing on the various methods available to us for the efficient size reduction of our training data. Special attention will be paid to which approaches are best suited for different data types and what impact the different approaches and compression rates have on the quality of the datasets. The compression library BigWhoop and its accompanying command line tool will be made available for the hands-on sessions.
The exercises will be carried out on both HLRS systems using Jupyter Notebooks and as interactive jobs on script.
The course language is English.
Students without Diploma/Master: 30 EUR
Students with Diploma/Master (PhD students) at German universities: 60 EUR
Members of German universities and public research institutes: 60 EUR
Members of universities and public research institutes within EU or PRACE member countries: 120 EUR.
Members of other universities and public research institutes: 240 EUR
Others: 300 EUR
HLRS is part of the Gauss Centre for Supercomputing (GCS), which is one of the six PRACE Advanced Training Centres (PATCs) that started in Feb. 2012.
HLRS is also member of the Baden-Württemberg initiative bwHPC-C5.
This course is provided within the framework of the bwHPC-C5 user Support.
This course is not part of the PATC curriculum and is not sponsored by the PATC program.