Contains all course materials from the HPML group Course environment: https://jupyter.snellius.surf.nl/jhssrf019
- Introduction to Deep Learning
- Using the PyTorch framework
- Fully connected networks, Convolutional networks, Transformers
- Software installations on HPC systems
- Packed file formats for Machine Learning
- Parallel computing for deep learning
- Hardware (e.g. Tensor cores) and software features (e.g. low level libraries for deep learning) for accelerated deep learning
- Profiling PyTorch with TensorBoard
09:00 – 9:20 Welcome and course overview (Lars Veefkind)
09:20 – 10:00 Introduction to ML & DL basic principles (Lars Veefkind)
10:00 – 10:30 Introduction to PyTorch (notebook) (Lars Veefkind)
10:30 – 10:45 Coffee break
10:45 – 11:30 Hands-on: Fully connected network (Lars Veefkind)
11:30 – 11:45 Recap Hands-on
11:45 – 12:45 Lunch Break
12:45 – 13:45 Convolutional neural networks (Lars Veefkind)
13:45 – 14:30 Hands-on: Convolutional neural networks (Lars Veefkind)
14:30 – 14:45 Recap hands-on
14:45 – 15:00 Coffee Break
15:00 – 15:45 LLMs / Transformers (Simone van Bruggen)
15:45 – 16:30 Hands-on/demo notebook: Transformers
16:30 – 17:00 Questions, wrap up
9:00 - 10:15 Parallel Computing for Deep Learning (Lars Veefkind)
10:15 – 10:30 Coffee break
10:30 – 11:00 Packed file formats (Monica Rotulo)
11:00 – 11:45 Hands-on: Packed file formats (Monica Rotulo)
11:45 – 12:45 Lunch Break
12:45 – 14:15 Software installations on HPC systems (Robert Jan Schlimbach/Monica Rotulo)
14:15 – 14:30 Coffee Break
14:30 – 15:15 Hardware and software features to accelerate deep learning (Monica Rotulo)
15:15 – 16:15 Profiling to understand your neural network’s performance (Robert Jan Schlimbach/Lars Veefkind)
16:15 – 17:00 Questions, wrap up