mlsanityData to 14 Oct 2026

Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons

arXiv 2506.20015 ↗First posted 24 Jun 2025cs.LG cs.IT cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Neuromorphic computing offers an energy-efficient alternative to conventional deep learning accelerators, particularly for real-time processing of time-series data. 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 45 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

16 of 45 references.

References · 16

  1. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  2. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 259
  3. 2019The Heidelberg spiking datasets for the systematic evaluation of spiking neural networkscited by 137
  4. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 115
  5. 2021Efficient Neuromorphic Signal Processing with Loihi 2cited by 96
  6. 2019DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measurescited by 56
  7. 2023Efficient Video and Audio processing with Loihi 2cited by 29
  8. 2019An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applicationscited by 26
  9. 2022Neuromorphic Wireless Cognition: Event-Driven Semantic Communications for Remote Inferencecited by 16
  10. 2024Balanced Resonate-and-Fire Neuronscited by 12
  11. 2022Neuromorphic Integrated Sensing and Communicationscited by 9
  12. 2023Knowing When to Stop: Delay-Adaptive Spiking Neural Network Classifiers with Reliability Guaranteescited by 8
4 more
  1. 2024Neuromorphic Split Computing with Wake-Up Radios: Architecture and Design via Digital Twinningcited by 7
  2. 2021A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network from Convolutional Neural Networkcited by 5
  3. 2024Neuromorphic Wireless Split Computing with Multi-Level Spikescited by 3
  4. 2024Direct Training Needs Regularisation: Anytime Optimal Inference Spiking Neural Networkcited by 2

Built on by

Not cited yet.