Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules

TL;DR

This paper introduces Spiking CapsNet, a biologically plausible spiking neural network that combines capsule networks with a novel routing mechanism, demonstrating robustness and high performance on image datasets.

Contribution

It proposes a new Spiking CapsNet model with a Spike Timing Dependent Plasticity routing rule, integrating capsule networks into spiking neural networks for improved coupling and robustness.

Findings

Achieves high accuracy on MNIST and FashionMNIST datasets.

Shows robustness to noise and affine transformations.

Outperforms other SNN models in experiments.

Abstract

Spiking neural network (SNN) has attracted much attention due to their powerful spatio-temporal information representation ability. Capsule Neural Network (CapsNet) does well in assembling and coupling features at different levels. Here, we propose Spiking CapsNet by introducing the capsules into the modelling of spiking neural networks. In addition, we propose a more biologically plausible Spike Timing Dependent Plasticity routing mechanism. By fully considering the spatio-temporal relationship between the low-level spiking capsules and the high-level spiking capsules, the coupling ability between them is further improved. We have verified experiments on the MNIST and FashionMNIST datasets. Compared with other excellent SNN models, our algorithm still achieves high performance. Our Spiking CapsNet fully combines the strengthens of SNN and CapsNet, and shows strong robustness to noise and affine transformation. By adding different Salt-Pepper and Gaussian noise to the test dataset, the experimental results demonstrate that our Spiking CapsNet shows a more robust performance when there is more noise, while the artificial neural network can not correctly clarify. As well, our Spiking CapsNet shows strong generalization to affine transformation on the AffNIST dataset.