# Spiking Approximations of the MaxPooling Operation in Deep SNNs

arXiv: https://arxiv.org/abs/2205.07076 · HTML: https://mlsanity.com/paper/2205.07076/

## Key facts

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

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Going Deeper in Spiking Neural Networks: VGG and Residual Architectures](https://mlsanity.com/paper/1802.02627/) (2018)
- [Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/1903.06530/) (2019)
- [Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing](https://mlsanity.com/paper/1603.08270/) (2016)
- [HFirst: A Temporal Approach to Object Recognition](https://mlsanity.com/paper/1508.01176/) (2015)
- [Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activations](https://mlsanity.com/paper/2003.10399/) (2020)
- [A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks](https://mlsanity.com/paper/1905.02704/) (2019)
- [A Spiking Neural Network for Image Segmentation](https://mlsanity.com/paper/2106.08921/) (2021)
- [SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron](https://mlsanity.com/paper/1903.02440/) (2019)
- [NengoDL: Combining deep learning and neuromorphic modelling methods](https://mlsanity.com/paper/1805.11144/) (2018)
- [DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networks](https://mlsanity.com/paper/2010.01795/) (2020)
- [An FPGA Implementation of Convolutional Spiking Neural Networks for Radioisotope Identification](https://mlsanity.com/paper/2102.12565/) (2021)

## Built on by (most cited first, 3 of 3)

- [Optical flow estimation from event-based cameras and spiking neural networks](https://mlsanity.com/paper/2302.06492/) (2023)
- [Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection](https://mlsanity.com/paper/2306.12010/) (2023)
- [Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network](https://mlsanity.com/paper/2407.01645/) (2024)

## 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.