NeuromorphicRx: From Neural to Spiking Receiver

2025-12-04

AI Summary

To address the high energy consumption and poor generalization of conventional receivers in 5G-NR OFDM systems, this paper proposes NeuromorphicRx—a novel neuromorphic receiver based on spiking neural networks (SNNs) that replaces channel estimation, equalization, and symbol demapping modules end-to-end. Methodologically, it incorporates domain knowledge into spike-encoded inputs, employs a deep convolutional SNN with residual connections, and adopts an ANN-SNN hybrid architecture to produce interpretable soft outputs. Training leverages surrogate gradient descent, quantization-aware training, and ablation studies for joint optimization. Experimental results demonstrate that NeuromorphicRx achieves strong robustness and cross-scenario generalization across diverse channel conditions, reduces energy consumption by 7.6× compared to conventional 5G-NR receivers, attains lower block error rates, and matches the performance of equivalently sized artificial neural network (ANN) baselines.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Mixture of Experts (MoE)
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• Designing an energy-efficient spiking neural network receiver for 5G-NR OFDM systems
• Replacing traditional channel estimation and equalization blocks with neuromorphic components
• Achieving robust performance with lower energy consumption compared to conventional receivers

Innovation

• Spiking neural network replaces channel estimation blocks
• Hybrid SNN-ANN architecture enables soft output generation
• Surrogate gradient descent trains energy-efficient 5G receiver