The Luxembourg SuperComputing Competence Center is hosting a webinar 4 March 2026.
Training description
Generative Adversarial Networks (GAN) are a type of Deep Neural Network (DNN) containing at least two networks within their structure – a Generator and a Discriminator. The Generator and the Discriminator play a competitive game against each other: The Generator tries to synthesize the most realistic data, e.g., images, videos, or signals, while the Discriminator is trained to distinguish real from fake (generated) data. The aim is to achieve equilibrium between these two neural networks, which requires a huge amount of data as well as a large amount of computation. Given that training GANs requires high-precision numerical operations and significant GPU memory resources, High Performance Computing (HPC) remains the method of choice, enabling efficient data loading, parallel training, the use of GPUs, faster model convergence, and reduction of training time. In this workshop, we will explore what types of GANs exist, where they are used, and why they are useful. We will also demonstrate how to use Distributed Data Parallel programming on HPC.
Target audience
This workshop is designed for anyone who would like to learn more about GANs and their practical applications.
GPU Compute Resources
During the training, participants will have access to the MeluXina supercomputer. For more information about MeluXina, please refer to the MeluXina Overview and the MeluXina – Getting Started Guide. Communication will take place via MicrosoftTeams and email. All training content will be provided in advance on GitHub.
Agenda
This one-day course will be hosted online in Central European Time (CET) on March 4, 2026 (09:00 AM – 05:00 PM).
Important: Limited spots available (25 participants max)!
Registration will close a week before the training date, on the 25 February 2026.
Contact person for more information: Aleksandra RANCIC – aleksandra.rancic[at]uni.lu
