Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons

2025-06-24

AI Summary

Conventional leaky integrate-and-fire (LIF) spiking neural networks (SNNs) struggle to efficiently model rich spectral features of streaming signals in edge wireless sensing and audio recognition, largely due to reliance on explicit spectral preprocessing and high spike rates. Method: This paper proposes a neuromorphic split-computing architecture for streaming signal processing, centered on resonant spiking neurons (RSNs) with intrinsic oscillatory dynamics. RSNs directly decode local spectral characteristics in the time domain, eliminating explicit spectral transformation; tunable resonance frequencies enable multi-scale time-frequency feature extraction while drastically reducing spike rates. The architecture integrates OFDM-based analog wireless spike transmission and an edge–end collaborative split-inference framework. Results: On audio classification and modulation recognition tasks, it achieves accuracy comparable to both LIF-SNNs and artificial neural networks (ANNs), while reducing end-to-end inference energy consumption by several orders of magnitude.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Learning on the Edge & Model Compression
• Natural Language Processing: Speech

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Neuromorphic computing offers an energy-efficient alternative to conventional deep learning accelerators for real-time time-series processing. However, many edge applications, such as wireless sensing and audio recognition, generate streaming signals with rich spectral features that are not effectively captured by conventional leaky integrate-and-fire (LIF) spiking neurons. This paper investigates a wireless split computing architecture that employs resonate-and-fire (RF) neurons with oscillatory dynamics to process time-domain signals directly, eliminating the need for costly spectral pre-processing. By resonating at tunable frequencies, RF neurons extract time-localized spectral features while maintaining low spiking activity. This temporal sparsity translates into significant savings in both computation and transmission energy. Assuming an OFDM-based analog wireless interface for spike transmission, we present a complete system design and evaluate its performance on audio classification and modulation classification tasks. Experimental results show that the proposed RF-SNN architecture achieves comparable accuracy to conventional LIF-SNNs and ANNs, while substantially reducing spike rates and total energy consumption during inference and communication.

Problem

• Enhancing spectral feature capture in neuromorphic wireless sensing
• Reducing energy consumption in real-time time-series processing
• Eliminating costly spectral pre-processing with resonate-and-fire neurons

Innovation

• Resonate-and-fire neurons for spectral feature extraction
• Wireless split computing with OFDM analog interface
• Temporal sparsity reduces energy consumption significantly