Education & Resources

Graphs are generic models of signal structure that can help to learn in several practical problems. To learn from graph data, we need scalable architectures that can be trained on moderate dataset sizes and that can be implemented in a distributed manner. Drawing from graph signal processing, the webinar will define graph convolutions and use them to introduce graph neural networks (GNNs). 

Signal sampling and reconstruction is a fundamental engineering task at the heart of signal processing. The celebrated Shannon-Nyquist theorem guarantees perfect signal reconstruction from uniform samples, obtained at a rate twice the maximum frequency present in the signal. 

The potentials of using millimeter-wave (mmWave) frequency for future wireless cellular communication systems have motivated the study of large-scale antenna arrays for achieving highly directional beamforming. However, the conventional fully digital beamforming methods, which require one radio frequency (RF) chain per antenna element, are not viable for large-scale antenna arrays due to the high cost and high power consumption of RF chain components in high frequencies.

In recent years, we have seen the emergence of new compute-intensive and delay-critical mobile applications, such as virtual/augmented reality, online gaming, ultra-high-definition video streaming and autonomous driving. Multi-access edge computing (MEC) has become a key technology in 5G networks to shift computational tasks from resource-limited mobile devices to nearby servers placed at the edge of the network.