This training session introduces Sionna - NVIDIA’s new open-source software library for GPU-accelerated link-level simulations and 6G research. It enables the rapid prototyping of complex communication system architectures and provides native support for the integration of neural networks. In this hands-on session, you will learn how set up realistic end-to-end link-level simulations by simply connecting the desired building blocks, such as OFDM modulation, 3GPP-compliant channel models, and 5G LDPC/Polar codes, which Sionna provides as TensorFlow Keras layers. You will learn how automatic differentiation allows for backpropagation of gradients through the entire system which can then be optimized for end-to-end performance. As a practical case study, you will replace a conventional OFDM receiver by a fully convolutional neural network and compare its end-to-end performance to that of a state-of-the-art baseline receiver. Prerequisite(s): A solid background in digital communication systems, especially the physical layer (OFDM, MIMO, modulation, detection, estimation, channel coding). Experience with Python and TensorFlow is beneficial.
*Please disregard any reference to "Event Code" for access to training materials. "Event Codes" are only valid during the original live session.
Explore more training options offered by the NVIDIA Deep Learning Institute (DLI). Choose from an extensive catalog of self-paced, online courses or instructor-led virtual workshops to help you develop key skills in AI, HPC, graphics & simulation, and more.