Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction
This addresses the need for efficient, low-power neural networks for embedded systems, though it appears incremental by building on existing SNN methods.
The paper tackles the problem of spatio-temporal feature extraction in convolutional spiking neural networks (SNNs), showing that a shallow convolutional SNN outperforms state-of-the-art methods like C3D and ConvLstm, and a new deep spiking architecture achieves superior performance on datasets such as NMNIST (99.6%), DVS-CIFAR10 (69.2%), and DVS-Gesture (96.7%).
Spiking neural networks (SNNs) can be used in low-power and embedded systems (such as emerging neuromorphic chips) due to their event-based nature. Also, they have the advantage of low computation cost in contrast to conventional artificial neural networks (ANNs), while preserving ANN's properties. However, temporal coding in layers of convolutional spiking neural networks and other types of SNNs has yet to be studied. In this paper, we provide insight into spatio-temporal feature extraction of convolutional SNNs in experiments designed to exploit this property. The shallow convolutional SNN outperforms state-of-the-art spatio-temporal feature extractor methods such as C3D, ConvLstm, and similar networks. Furthermore, we present a new deep spiking architecture to tackle real-world problems (in particular classification tasks) which achieved superior performance compared to other SNN methods on NMNIST (99.6%), DVS-CIFAR10 (69.2%) and DVS-Gesture (96.7%) and ANN methods on UCF-101 (42.1%) and HMDB-51 (21.5%) datasets. It is also worth noting that the training process is implemented based on variation of spatio-temporal backpropagation explained in the paper.