Benchmarking spiking neural networks across sensing modalities on edge devices

• URL: http://arxiv.org/abs/2609.00026v1
• Date: Thu, 27 Aug 2026 06:23:21 GMT
• Title: Benchmarking spiking neural networks across sensing modalities on edge devices
• Abstract summary: Spiking neural networks (SNNs) are a promising alternative to conventional artificial neural networks (ANNs)<n>We present a benchmark of SNNs across five sensing modalities and multiple edge devices.<n>We find that SNN advantages are strongly modality-dependent, while wireless sensing emerges as a particularly favorable domain.
• Score: 43.191205262610026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Edge computing systems need to support diverse sensing workloads under tight energy and memory constraints, thereby motivating deployment-aware model selection. Spiking neural networks (SNNs) are a promising alternative to conventional artificial neural networks (ANNs), yet systematic evidence for when and why they provide practical advantages remains limited. Here, we present a benchmark of SNNs across five sensing modalities and multiple edge devices, systematically evaluating spike encoding, neuron models, and network topologies under consistent training and deployment protocols. We find that SNN advantages are strongly modality-dependent: while SNNs achieve performance broadly comparable to ANNs across most workloads, wireless sensing emerges as a particularly favorable domain. Frequency-domain and feature-space analyses further explain this result by showing that spiking dynamics naturally align with the spectral-temporal structure of wireless signals. Our deployment analysis further shows that SNN advantages are not one-dimensional, with energy gains often accompanied by modality-dependent system costs. Finally, we provide an open-source framework for reproducible benchmarking and deployment profiling, offering a practical foundation for algorithm-software-hardware co-design on emerging edge and neuromorphic computing platforms.

Related papers

• Event-based Heterogeneous Information Processing for Online Vision-based Obstacle Detection and Localization [0.3499870393443268]
  This paper introduces a novel framework for robotic vision-based navigation that integrates Hybrid Neural Networks (HNNs) with Spiking Neural Network (SNN)-based filtering.<n>By leveraging the complementary strengths of Artificial Neural Networks (ANNs) and SNNs, the system achieves both accurate environmental understanding and fast, energy-efficient processing.
  arXiv  Detail & Related papers  (2026-01-19T23:09:23Z)
• Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control [59.65431931190187]
  Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision making on neuromorphic hardware.<n>Most continuous control algorithms for continuous control are designed for Artificial Neural Networks (ANNs)<n>We show that this mismatch destabilizes SNN training and degrades performance.<n>We propose a novel proxy target framework to bridge the gap between discrete SNNs and continuous-control algorithms.
  arXiv  Detail & Related papers  (2025-05-30T03:08:03Z)
• Causal pieces: analysing and improving spiking neural networks piece by piece [2.255961793913651]
  We introduce a novel concept for spiking neural networks (SNNs) derived from the idea of "linear pieces"<n>We prove that the input domain of SNNs decomposes into distinct causal regions where its output spike times are locally Lipschitz continuous.<n>The number of such regions - which we call "causal pieces" - is a measure of the approximation capabilities of SNNs.
  arXiv  Detail & Related papers  (2025-04-18T18:07:33Z)
• Exploring Neural Network Pruning with Screening Methods [3.443622476405787]
  Modern deep learning models have tens of millions of parameters which makes the inference processes resource-intensive.<n>This paper proposes and evaluates a network pruning framework that eliminates non-essential parameters.<n>The proposed framework produces competitive lean networks compared to the original networks.
  arXiv  Detail & Related papers  (2025-02-11T02:31:04Z)
• Applications of Spiking Neural Networks in Visual Place Recognition [19.577433371468533]
  Spiking Neural Networks (SNNs) are increasingly recognized for their potential energy efficiency and low latency.<n>This paper highlights three advancements for SNNs in Visual Place Recognition (VPR)<n> Firstly, we propose Modular SNNs, where each SNN represents a set of non-overlapping geographically distinct places.<n> Secondly, we present Ensembles of Modular SNNs, where multiple networks represent the same place.<n> Lastly, we investigate the role of sequence matching in SNN-based VPR, a technique where consecutive images are used to refine place recognition.
  arXiv  Detail & Related papers  (2023-11-22T06:26:24Z)
• Inherent Redundancy in Spiking Neural Networks [24.114844269113746]
  Spiking Networks (SNNs) are a promising energy-efficient alternative to conventional artificial neural networks. In this work, we focus on three key questions regarding inherent redundancy in SNNs. We propose an Advance Attention (ASA) module to harness SNNs' redundancy.
  arXiv  Detail & Related papers  (2023-08-16T08:58:25Z)
• A Hybrid Neural Coding Approach for Pattern Recognition with Spiking Neural Networks [53.31941519245432]
  Brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks. These SNNs are grounded on homogeneous neurons that utilize a uniform neural coding for information representation. In this study, we argue that SNN architectures should be holistically designed to incorporate heterogeneous coding schemes.
  arXiv  Detail & Related papers  (2023-05-26T02:52:12Z)
• Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
  "smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
  arXiv  Detail & Related papers  (2022-09-27T15:04:01Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks [80.15411508088522]
  Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency. We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
  arXiv  Detail & Related papers  (2020-07-02T15:38:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.