mlsanityData to 7 Oct 2026

Spiking Approximations of the MaxPooling Operation in Deep SNNs

arXiv 2205.07076 ↗First posted 14 May 2022cs.NE cs.AI cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Spiking Neural Networks (SNNs) are an emerging domain of biologically inspired neural networks that have shown promise for low-power AI. A number of methods exist for building deep SNNs, with Artificial Neural Network (ANN)-to-SNN conversion being highly successful. MaxPooling layers in Convolutional Neural Networks (CNNs) are an integral component to downsample the intermediate feature maps and introduce translational invariance, but the absence of their hardware-friendly spiking equivalents limits such CNNs' conversion to deep SNNs. In this paper, we present two hardware-friendly methods to implement Max-Pooling in deep SNNs, thus facilitating easy conversion of CNNs with MaxPooling layers to SNNs. In a first, we also execute SNNs with spiking-MaxPooling layers on Intel's Loihi neuromorphic hardware (with MNIST, FMNIST, & CIFAR10 dataset); thus, showing the feasibility of our approach.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 15 of its 34 references that are in the map. First posted on arXiv 14 May 2022.

Builds on

15 of 34 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  4. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  5. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 236
  6. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 174
  7. 2016Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computingcited by 68
  8. 2015HFirst: A Temporal Approach to Object Recognitioncited by 50
  9. 2020Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activationscited by 47
  10. 2019A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networkscited by 35
  11. 2021A Spiking Neural Network for Image Segmentationcited by 27
  12. 2019SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuroncited by 23
3 more
  1. 2018NengoDL: Combining deep learning and neuromorphic modelling methodscited by 11
  2. 2020DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networkscited by 4
  3. 2021An FPGA Implementation of Convolutional Spiking Neural Networks for Radioisotope Identificationcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2023Optical flow estimation from event-based cameras and spiking neural networkscited by 33
  2. 2023Spiking Neural Network for Ultra-low-latency and High-accurate Object Detectioncited by 14
  3. 2024Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Networkcited by 5