Description and Aim
The aim of this course is to give an introduction to machine learning (deep learning) and an overview of how different techniques can be applied to CFD problems.
Through hands-on exercises in computer vision and natural language processing, you’ll train deep learning models from scratch, learning tools and tricks to achieve highly accurate results. You’ll also see how to leverage freely available, state-of-the-art pre-trained models to save time and get your deep learning application up and running quickly.
Who this course is for
The course is for beginners in deep learning. No prior CFD knowledge is required, but un understanding of it will help to clarify how to eventually integrate the different methodologies into their problems. Basic concepts in Python 3, such as functions, loops, dictionaries, and arrays is required.
What you will learn
- The fundamental techniques and tools required to train a deep learning model
- Gain experience with common deep learning data types and model architectures
- Enhance datasets through data augmentation to improve model accuracy
- Leverage transfer learning between models to achieve efficient results with less data and computation
- Build confidence to take on your own project with a modern deep learning framework
- Get an overview of current machine learning approaches used in CFD
What you will need
Only your laptop with a browser (Chrome ideally) for your internet connection.
Attendance logistics
This course is free to attend for all and refreshments plus lunch will be provided on both days, however travel and accommodation is not covered.
Agenda
Monday 4th November 2024
| 12:00 – 13:30 | Lunch |
| 13:00 – 14:00 | Introduction to Deep Learning (NVidia Deep Learning Institute) |
| 14:00 – 15:00 | How a Neural Network Trains |
| 15:00 – 15:30 | Coffee break |
| 15:30 – 16:30 | Convolutional Neural Networks |
| 16:30 – 17:30 | Data Augmentation and Deployment |
Tuesday 5th November 2024
| 09:00 – 09:45 | Pre-trained Model |
| 09:45 – 10:30 | Advanced Architectures |
| 10:30 – 11:00 | Coffee Break |
| 11:00 – 12:30 | Some Literature overview on Deep Learning for Turbulence |
| 12:30 – 13:30 | Lunch break |
| 13:30 – 15:00 | Test case: StyleGAN as deconvolution operator for LES in BOUT++ |
Registration for this event has closed.