SciML GPU Bootcamp

Welcome to this SciML GPU Bootcamp! This online event will take place during two half-days on 21-22 February 2023 and is designed to teach researchers and engineers how scientific machine learning (SciML) can address domain-specific data challenges and extract insights from scientific datasets. The Bootcamp is co-organised by ENCCS, OpenACC.org and NVIDIA.

SciML is an emerging multidisciplinary field which includes elements from applied and computational mathematics, computer science and the physical sciences. In particular, physics-informed neural networks (PINNs), a class of Deep Learning (DL) networks, can be applied to scientific applications solving linear and non-linear equations with demanding accuracy and computational performance requirements. PINNs are specifically designed to integrate scientific computing equations, such as Ordinary Differential Equations (ODE), Partial Differential Equations (PDE), non-linear and integral-differential equations into the DL network training.

This bootcamp introduces SciML with PINNs and gives participants a hands-on experience with working on a PDE solver NVIDIA Modulus, a neural network framework that blends the power of physics in the form of governing PDEs with data to build high-fidelity, parameterized surrogate models with near-real-time latency. You will be guided through step-by-step instructions with teaching assistants to study the core concepts of neural operators, PINNs, and how to apply them to scientific problems.

The bootcamp will be hosted online in the Central European Time (CET) zone. All communication will be done through Zoom, HackMD and email.

Event Format

The bootcamp will be hosted online in the Central European Time (CET) zone. All communication will be done through Zoom, HackMD and email.

Prerequisites

Basic experience with Python. No GPU programming or AI knowledge is required.

This event has limited capacity, so please make sure that prerequisites are met before applying. You will be receiving an acceptance email with details on how to participate.

Compute Resources

Teams attending the event will be given access to a EuroHPC GPU cluster for the duration of the hackathon.

Agenda

Day 1, February 21

Day 2, February 22

Registration

Please register by following this link https://events.prace-ri.eu/event/1461/registrations/1077/
Application deadline: February 7

Contact

For any questions contact us at training@enccs.se

Follow our Events Schedule