Guest talk: Jakob Hoydis "Deep-Learning for the Physical Layer with Sionna"
Dr. Jakob Hoydis from NVIDIA will give a guest talk at the Department of Computer Science.
![Jakob Hoydis_Deep-Learning for the Physical Layer with Sionna](/sites/g/files/flghsv161/files/styles/1_300w_300h_n/public/2022-09/Deep-Learning%20for%20the%20Physical%20Layer%20with%20Sionna.png?h=0cb88eef&itok=CWNXNndA)
When
–
Where
Lecture hall Lumituuli
Event language(s)
English
Deep-Learning for the Physical Layer with Sionna
Jakob Hoydis
NVIDIA
Abstract: Sionna is an open-source, GPU-accelerated, and fully differentiable link-level simulator for 6G research. One of its main features is automatic gradient computation through an entire end-to-end system which allows for seamless integration and training of neural networks. After a short introduction explaining the motivation behind Sionna, its features and design principles, I will discuss several of our recent research results, including synchronization for NB-IoT as well as GNN-based channel decoding.
- Published:
- Updated: