Learn how AI can accelerate HPC simulations by introducing students to concepts of Deep Neural Networks, including data pre-processing, techniques on how to build, compare and improve accuracy of deep learning models. Bootcamp will introduce real-life problems, where participants learn AI concepts following step-by-step instructions and then given an opportunity to improve the taught solution using learned techniques.
The bootcamp will be hosted online in the pacific time zone. All communication will be done through Zoom, Slack and email.
Basic experience with Python. No GPU programming or AI knowledge is required.
Deadline to apply: October 28, 2020
Day 1 (Intro): November 4, 2020
- Welcome (Moderator): 9:00 AM PDT
- Connecting to a cluster: 9:15AM - 9:30 AM PDT
- Introduction to GPU computing: 9:30AM - 10:00AM PDT (Lecture)
- Introduction to AI: 10:00AM - 11:00AM PDT (Lecture)
- CNN Primer and Keras 101: 11:00AM - 12:00PM PDT (Lecture and Lab)
Day 2 (Advanced): November 5, 2020
- Tropical cycle detection: 9:00AM - 10:30AM PDT (Lab + Challenge)
- Break 10:30-10:45AM PDT
- Steady Flow Estimation 10:45AM - 12:15PM (Challenge)
Participants will have access to Simon Fraser University's Supercomputer Cedar which is one of the most powerful academic supercomputers in Canada. Cedar provides the scale and capacity that is paving the way for new research breakthroughs. Cedar provides the computing power Canadian researchers need to achieve transformational innovations that directly benefit Canadians. Just some of these include personalized medicine for better patient care, green technologies to help fight climate change, and artificial intelligence research that will contribute to the Canadian economy.
Cedar is one of five national systems Compute Canada has deployed as part of one of the biggest advanced research computing renewals in Canada’s history.