![]() Meanwhile, our ablation study demonstrates that STCA-SNNs improve the accuracy of event stream classification tasks.Īs the representatives of mimicking the human brain at the neuronal level, Spiking Neural Networks (SNNs) have gained great attraction for the high biological plausibility, event-driven property, and high energy efficiency ( Rieke et al., 1999 Gerstner et al., 2014 Bellec et al., 2018). Our experimental results show that STCA-SNNs achieve better performance on N-MNIST (99.67%), CIFAR10-DVS (81.6%), and N-Caltech 101 (80.88%) compared with the state-of-the-art SNNs. ![]() It models global temporal and channel information correlations with self-attention, enabling the network to learn ‘what’ and ‘when’ to attend simultaneously. To leverage the temporal potential of SNNs, we propose a self-attention-based temporal-channel joint attention SNN (STCA-SNN) with end-to-end training, which infers attention weights along both temporal and channel dimensions concurrently. With intrinsic event-triggered property and temporal dynamics, SNNs have the potential to effectively extract spatio-temporal features from event streams. However, there remains a performance gap between SNNs and ANNs, which impedes the practical application of SNNs. Spiking Neural Networks (SNNs) have shown great promise in processing spatio-temporal information compared to Artificial Neural Networks (ANNs). School of Optics and Photonics, Beijing Institute of Technology, Beijing, China.Xiyan Wu Yong Song * Ya Zhou * Yurong Jiang Yashuo Bai Xinyi Li Xin Yang
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |