NeuromorphicRx: From Neural to Spiking Receiver

TL;DR

This paper introduces NeuromorphicRx, an energy-efficient spiking neural network-based receiver for 5G-NR systems, replacing traditional blocks and achieving high performance with significantly lower energy use.

Contribution

The work presents a novel neuromorphic receiver architecture for 5G-NR, combining SNNs with ANNs, and demonstrates its effectiveness and energy efficiency through extensive simulations.

Findings

Achieves significant block error rate improvements over traditional 5G-NR receivers.

Maintains comparable performance to ANN-based receivers with 7.6x less energy consumption.

Demonstrates robustness and generalization across diverse 5G-NR scenarios.

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.