Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules
This work addresses the challenge of enhancing biologically plausible neural networks for tasks like image classification, though it appears incremental as it combines existing SNN and CapsNet concepts.
The authors tackled the problem of integrating capsule networks with spiking neural networks to improve feature coupling and robustness, resulting in a model that achieves high performance on MNIST and FashionMNIST datasets and demonstrates strong robustness to noise and affine transformations.
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.