NCSA Research Consulting Training Events

In this session, we will introduce the essential concepts of deep learning: neural networks and how to train them. We will use the Illinois Computes Research Notebooks (ICRN) which provides a Jupyter interface and access to GPUs, to demonstrate the concepts.  Participants will gain an understanding of essential components of neural network training such as loss functions, optimizers, and key architectural components.  Participants will learn how to implement a basic neural network using PyTorch and train it on GPUs.  PyTorch, widely recognized for its flexibility and ease of use, is one of the most popular choices for deep learning in both academic research and industry applications.

This training aims to build both theoretical knowledge and practical skills, equipping participants to advance in the field of deep learning.  No prior knowledge of deep learning is necessary, but familiarity with Jupyter, Python and NumPy will help.