NeuromorphicRx: From Neural to Spiking Receiver
Ankit Gupta, Onur Dizdar, Yun Chen, Fehmi Emre Kadan, Ata Sattarzadeh, Stephen Wang
TL;DR
This work introduces NeuromorphicRx, an energy-efficient SNN-based receiver for 5G-NR OFDM that replaces multiple traditional signal-processing blocks. It leverages domain-aware input encoding, a deep SEW ResNet of spiking neurons, and a hybrid SNN-ANN readout to produce soft outputs, trained with surrogate gradients and quantization-aware techniques for robustness. Empirical results show NeuromorphicRx nearly matches ANN-based NeuralRx performance while achieving up to 7.6x energy savings, with further improvements under quantization. The approach highlights the practicality of neuromorphic receivers for power-constrained wireless devices and outlines pathways for end-to-end neuromorphic transceivers and JSCC.
Abstract
In this work, we propose a novel energy-efficient spiking neural network (SNN)-based receiver for 5G-NR OFDM system, called neuromorphic receiver (NeuromorphicRx), replacing the channel estimation, equalization and symbol demapping blocks. We leverage domain knowledge to design the input with spiking encoding and propose a deep convolutional SNN with spike-element-wise residual connections. We integrate an SNN with artificial neural network (ANN) hybrid architecture to obtain soft outputs and employ surrogate gradient descent for training. We focus on generalization across diverse scenarios and robustness through quantized aware training. We focus on interpretability of NeuromorphicRx for 5G-NR signals and perform detailed ablation study for 5G-NR signals. Our extensive numerical simulations show that NeuromorphicRx is capable of achieving significant block error rate performance gain compared to 5G-NR receivers and similar performance compared to its ANN-based counterparts with 7.6x less energy consumption.