The IEEE Finland Jt. Chapter SP01/CAS04 like to acknowledge the participation of the Signal Processing Society (SPS) distinguished industry speaker program (DISP): Dr.-Ing. Jakob Hoydis on the Workshop on Signal Processing and Circuits and Systems organized on October 05th of 2022. This event was organized as an hybrid event (Zoom and in-person). The in-person event was taking place in the lecture hall Lumituuli in the Dipoli building of Aalto University, Otaniemi, Espoo, Finland.

The event count with 20+ in-person participants and more than 70+ remote participants by Zoom connected from different remote areas in Finland (Oulu, Lappeenranta, Tampere).

Dr.-Ing. Jakob Hoydis (website) contributed on this workshop with the presentation titled: “Deep-Learning for the Physical Layer with Sionna”.

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.

Jakob Hoydis during his presentation in the Workshop organized by the IEEE SPS/CAS Chapter in Finland on October 5th 2022.