- https://www.nat-esm.de/services/workshops-and-trainings/events/ai-bootcamp
- BOOTCAMP: AI for Science Bootcamp
- 2023-04-17T00:00:00+02:00
- 2023-04-18T23:59:59+02:00
- This training course will be held online.
Apr 17, 2023
to
Apr 18, 2023
(Europe/Berlin / UTC200)
Online
During this two-day online Bootcamp, participants will learn how to apply AI tools, techniques and algorithms to real-life problems. You will study the core concepts of Deep Neural Networks, how to build Deep Learning models as well as how to measure and improve the accuracy of your models. You will also learn essential data pre-processing techniques to ensure a robust Machine Learning pipeline. This online Bootcamp is a hands-on learning experience where you will be guided through step-by-step instructions with teaching assistants on hand to help throughout.
The Bootcamp is co-organised by HLRS, JSC, LRZ, VSC, OpenACC.org and NVIDIA for EuroCC Austria and EuroCC@GCS, the Austrian and German National Competence Centres for High-Performance Computing.
Prerequisites:
Basic experience with Python. No GPU programming or AI knowledge is required.
Content levels:
- Intermediate level: 3,5 hours
- Advanced level: 3,5 hours
Learn more about course curricula and content levels.
Language
All lectures will be given in English.
Agenda - preliminary -
Cluster Dry Run: Monday, April 17th: 11:30 AM - 12:30 PM
Day 1 (April 17, afternoon): Introduction
1:30 PM - 1:45 PM: Welcome (Moderator)
1:45 PM - 2:30 PM: Introduction to GPU computing (Lecture)
2:30 PM - 3:30 PM: Introduction to AI (Lecture)
3:30 PM - 5:00 PM: CNN Primer and Keras (hands-on lab)
Day 2 (April 18, afternoon): Advanced Topics
1:30 PM - 3:00 PM: Tropical cycle detection (Lab + Challenge)
3:00 PM - 3:15 PM: Break
3:15 PM - 4:45 PM : Steady Flow Estimation (Challenge)
4:45 PM - 5:00 PM: Wrap up and QA
Hands-on sessions
Attendees will be given access to a GPU cluster for the duration of the Bootcamp.
The code is publicly available on github (climate and CFD).
Registration information
The course is open and free of charge for participants from academia and industry.
Please register at OpenACC-Standard.org with your institutional e-mail address to prove your affiliation.
The final participants will be selected and informed after the registration deadline has passed.
Registration closes on March 28, 2023 at 23:55.