Mutual Information Analysis of Neuromorphic Coding for Distributed Wireless Spiking Neural Networks

Wireless Spiking neural networks (WSNNs) allow energy-efficient device-to-device (D2D) or vehicle-to-everything (V2X) communications, especially while considering edge intelligence and learning for beyond 5G and 6G systems. Recent research work has revealed that distributed wireless SNNs (DWSNNs) show good performance in terms of inference accuracy and low energy consumption of edge devices, under the constraints of limited bandwidth and spike loss probability. In this work, we focus on neuromorphic, AI-native transmission techniques for DWSNNs, quantitatively evaluating the features of different coding algorithms that can be viewed as impulse radio modulations. Specifically, the main contribution of this work is the evaluation of information-theoretic measures that may help in quantifying performance trade-offs among existing neuromorphic coding techniques.