mlsanityData to 14 Oct 2026

EdgeSpike: Spiking Neural Networks for Low-Power Autonomous Sensing in Edge IoT Architectures

arXiv 2604.27004 ↗First posted 29 Apr 2026cs.NE cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose EdgeSpike, a co-designed spiking neural network (SNN) framework for autonomous low-power sensing in edge Internet of Things (IoT) architectures. EdgeSpike unifies (i) a hybrid surrogate-gradient and direct-encoding training pipeline, (ii) a hardware-aware neural architecture search (NAS) bounded by per-inference energy and memory budgets, (iii) an event-driven runtime targeting Intel Loihi 2, SpiNNaker 2, and commodity ARM Cortex-M microcontrollers with custom spike-sparse SIMD kernels, and (iv) a lightweight local plasticity rule enabling continual on-device adaptation without backpropagation. The framework is evaluated across five sensing tasks (keyword spotting, vibration-based machine fault detection, surface electromyography gesture recognition, 77 GHz radar human-activity classification, and structural-health acoustic-emission monitoring) on three hardware targets. EdgeSpike achieves a mean classification accuracy of 91.4%, within 1.2 percentage points (pp) of strong INT8 convolutional neural network (CNN) baselines (mean 92.6%), while reducing energy per inference by 18x to 47x on neuromorphic hardware (mean 31x) and by 4.6x to 7.9x on Cortex-M (mean 6.1x). End-to-end latency remains at or below 9.4 ms across all 15 task-hardware configurations. A seven-month, 64-node wireless field deployment confirms a 6.3x extension in projected battery lifetime (from 312 to 1978 days at 2 Wh per node) and bounded accuracy degradation under seasonal drift (0.7 pp with on-device adaptation versus 2.1 pp without). Hardware-aware NAS evaluates 8400 candidates and yields a 12-point Pareto front. EdgeSpike will be released as open source with reproducible training pipelines, hardware-portable runtimes, and benchmark suites.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 51 references that are in the map. First posted on arXiv 29 Apr 2026.

Builds on

28 of 51 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  6. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  7. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  8. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  9. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  10. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 434
  11. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  12. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
16 more
  1. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 278
  2. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
  3. 2018Deep Learning in Spiking Neural Networkscited by 263
  4. 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 182
  5. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 165
  6. 2020Sparse GPU Kernels for Deep Learningcited by 141
  7. 2021MLPerf Tiny Benchmarkcited by 124
  8. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 121
  9. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 115
  10. 2017Hello Edge: Keyword Spotting on Microcontrollerscited by 110
  11. 2024Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chipscited by 103
  12. 2017Deep Residual Learning for Small-Footprint Keyword Spottingcited by 68
  13. 2022Neural Architecture Search for Spiking Neural Networkscited by 53
  14. 2015Memory and information processing in neuromorphic systemscited by 48
  15. 2022AutoSNN: Towards Energy-Efficient Spiking Neural Networkscited by 40
  16. 2021The SpiNNaker 2 Processing Element Architecture for Hybrid Digital Neuromorphic Computingcited by 14

Built on by

Not cited yet.