Data analytics for engineering data using machine learning

Description

This three-day online workshop addresses the preparation, analysis and interpretation of numerical simulation data by machine learning methods. Besides the introduction of the most important concepts like clustering, dimensionality reduction, visualization and prediction, this course provides several practical hands-on tutorials using the python libraries numpy, scikit-learn and pytorch as well as the SCAI DataViewer (see also the SimExplore tool).

 

Learning outcomes

• Basic knowledge on important machine learning methods to analyze numerical simulation data.
• Moreover, practical experience in applying these methods.

 

Target audience

Researchers, developers and industrial end users interested in new ways to analyze and visualize numerical simulation data.

 

Location

Online course
Organizer: HLRS, University of Stuttgart, Germany

 

Prerequisites and content levels

 

Prerequisites

• Preliminary experience with Python is required. Since Python is used, the following tutorial can be used to learn the syntax.
• Preliminary experience in using Jupyter Notebook is also required.

Content levels

• Beginners' level: 4 hours
• Intermediate level: 5 hours
• Community level: 5 hours

Learn more about course curricula and content levels.

 

Instructors

Arno Feiden, Christian Gscheidle and Daniela Steffes-lai (Fraunhofer SCAI)

 

Agenda

CET times:

 

Day 1: 4 November 2024

• 08:45-09:00 Drop in to the videoconference
• 09:00-12:30 Introduction to machine learning methods like clustering and dimensionality reduction by means of short practical exercises in python
• 12:30-13:30 Lunch break
• 13:30-17:00 Application of the methods from the previous session to numerical simulation data stemming from engineering applications with the help of the SCAI DataViewer

 

Day 2: 5 June 2024

• 08:45-09:00 Drop in to the videoconference
• 09:00-12:30 Introduction to prediction by deep learning methods together with hands-on exercises using the software library pyTorch

 

Day 3: 6 June 2024

• 08:45-09:00 Drop in to the videoconference
• 09:00-12:30 Introduction to interpretability of machine learning methods with the help of the examples from the previous session

 

Handout

Notebooks and data will be already available on the EXCELLERAT P2 Portal (for registered users only). 

Updated exercises and slides will be made available during the course.

 

Registration information

Register at Fraunhofer SCAI via the button at the top of this page.

 

Fees

• Students without master’s degree or equivalent: 300 EUR
• PhD students or employees at a German university or public research institute: 300 EUR
• PhD students or employees at a university or public research institute in an EU, EU-associated or PRACE country other than Germany: 300 EUR
• PhD students or employees at a university or public research institute outside of EU, EU-associated or PRACE countries: 600 EUR
• Other participants, e.g., from industry, other public service providers, or government: 600 EUR

Link to the EU and EU-associated (Horizon Europe), and PRACE countries.

 

If you are an EXCELLERAT Member, special conditions are available.

 

Contact

Maksym Deliyergiyev, phone 0711 685 87261, maksym.deliyergiyev(at)hlrs.de

 

HLRS Training Collaborations in HPC

HLRS is part of the Gauss Centre for Supercomputing (GCS), together with JSC in Jülich and LRZ in Garching near Munich.  is the German National Competence Centre (NCC) for High-Performance Computing. HLRS is also a member of the Baden-Württemberg initiative bwHPC.

 

This course is partly realised in cooperation with the Centre of Excellence EXCELLERAT P2 (funded by the European Union, grant agreement No 101092621). See also the EXCELLERAT Service Portal for more information.