The ARISTIDES project aims to deepen the theoretical understanding and advance on the performance of data-driven learning and inference algorithms for high-dimensional data processing. A special focus is set on the enhancement of machine learning methods (incl. deep learning) and their application to the re-design of lower-layer functionalities of beyond 5G and 6G communication systems. The demo showcased at EuCNC/6G Summit22 illustrates how deep learning can shape the future of coding and modulation schemes and pave the way towards a fully AI-native air interface for 6G. Specifically, we focus on an uplink NOMA (Non-Orthogonal Multiple-Access) scenario with two transmitters and one receiver and demonstrates how AI-based designs exhibit higher reliability when compared with classical ones based on QAM modulation schemes. Disruptive 3D constellations adapting to the time-varying nature of the propagation environment will be displayed via hologram projections. The ARISTIDES project (RTI2018-099722-B-I00) is funded by MCIN/AEI/10.13039/501100011033 and by “ERDF A way of making Europe”.
