The Hartree Centre is collaborating with NVIDIA on a two-day RAPIDS bootcamp. You'll have the opportunity to learn how to apply AI tools and techniques to several applications ranging from medical image analysis to product assistance.
When: 17 - 18 February 2022 | 09:00 - 12:30
Where: Online event
Best for: Users with basic experience in Python
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.
Agenda
Day 1 (Introduction): February 17, 2022 (All times are GMT)- 09:00 AM - 09:15 AM: Welcome by Hartree Centre CSO Prof V.N. Alexandrov
- 09:15 AM - 09:30 AM: Connecting to a cluster
- 09:30 AM - 10:30 AM: Intro to RAPIDS Ecosystem
- 10:30 AM - 11:30 AM: Lab 1: Using RAPIDS CuDF
- 11:30 AM - 12:30 PM: Lab 2: Using RAPIDS CuML
- 11:00 PM - 12:00 PM: CNN Primer and Keras 101 (Lecture and Lab)
Day 2 (Advanced): February 18, 2022 (All times are GMT)- 09:00 AM - 10:00 AM: Lab 3: Using RAPIDS Dask ( Multi-GPU )
- 10:00 AM - 12:15 PM: Gene Expression Classification/Bike Rental Prediction (Mini challenge)
(Participants convert SkLearn based real-world examples to using RAPIDS) - 12:15 PM - 12:30 PM : Q&A and Wrap Up
Event format
This 2-day Bootcamp will be hosted online in the Greenwich Mean Time (GMT) zone. All communication will be done through Zoom, Slack and email.
Prerequisites
Basic experience with Python. No GPU programming or AI knowledge is required.
Compute resources
Attendees will be given access to JADE 2 Deep Learning supercomputer for the duration of the Bootcamp.