NERSCPowering Scientific Discovery for 50 Years

NERSC/NVIDIA AI for Scientific Computing Bootcamp: Oct. 18-20, 2023

October 18, 2023

NERSC, in collaboration with the OpenACC organization and NVIDIA, is hosting a virtual, three-day AI for Scientific Computing Bootcamp from Wednesday, October 18, through Friday, October 20, 2023.

This bootcamp will provide a step-by-step overview of the fundamentals of deep neural networks and walk attendees through the hands-on experience of building and improving deep learning models for applications related to scientific computing and physical systems defined by differential equations. It will also cover more advanced topics, such as physics-informed neural networks (PINNs) and operator learning. Bootcamp attendees will use tools like NVIDIA Modulus to develop and train the models and NVIDIA Omniverse to visualize the results of model predictions.

Eligibility and Attendance

This event will be held virtually and is open to the general HPC community. However, due to limited capacity, active NERSC, ALCF, and OLCF users will receive priority consideration. 


Attendees should have

  • Basic experience with Python and PyTorch, and
  • Basic knowledge of neural networks (recommended but not required).

GPU programming experience is not required.

Event Format

The event will be hosted online in Pacific Daylight Time (GMT/UTC-7). All communication will be done through Zoom, Slack, and email. Attendees will be given access to a GPU cluster for the duration of the bootcamp. 


All times are Pacific Daylight (PDT/UTC-7).

Day 0 // Tuesday, October 17
11 a.m. -12 p.m. Cluster Dry Run Session
Day 1 // Wednesday, October 18
9 - 9:15 a.m. Welcome (Moderator)
9:15 - 9:30 a.m Connecting to a cluster
9:30 - 10 a.m. Introduction to NVIDIA Modulus (Lecture)
10 a.m. - 12 p.m. Building Physics-Informed Neural Network using NVIDIA Modulus (Lecture and Lab)
Day 2 // Thursday, October 19
9 - 10:30 a.m. Physics-Informed approach to an AI for Science application. (Lecture and Lab) 
10:30 a.m. - 12:15 p.m Data-driven approach to an AI for Science application. (Lecture and Lab)
12:15 - 12:30 p.m. Wrap-up and Q&A
Day 3 // Friday, October 20
9 - 10:30 a.m. Introduction to NVIDIA Omniverse: Basic Tools (Lecture)
10:30 - 10:45 a.m Break
10:45 - 12:15 p.m. Application Visualization Using Omniverse Extensions (Lab)
12:15 - 12:30 p.m. Wrap-up and Q&A
12:30 p.m. Adjourn

How to Apply

Visit the bootcamp event page to apply and for more details. Applying does not guarantee attendance. Confirmed attendees will receive an email prior to the bootcamp.


To be considered, you must apply by October 4, 2023.