Author:
Zhao Zihao,Wang Yanhong,Zou Qiaosha,Xu Tie,Tao Fangbo,Zhang Jiansong,Wang Xiaoan,Shi C.-J. Richard,Luo Junwen,Xie Yuan
Abstract
Action recognition is an exciting research avenue for artificial intelligence since it may be a game changer in emerging industrial fields such as robotic visions and automobiles. However, current deep learning (DL) faces major challenges for such applications because of the huge computational cost and inefficient learning. Hence, we developed a novel brain-inspired spiking neural network (SNN) based system titled spiking gating flow (SGF) for online action learning. The developed system consists of multiple SGF units which are assembled in a hierarchical manner. A single SGF unit contains three layers: a feature extraction layer, an event-driven layer, and a histogram-based training layer. To demonstrate the capability of the developed system, we employed a standard dynamic vision sensor (DVS) gesture classification as a benchmark. The results indicated that we can achieve 87.5% of accuracy which is comparable with DL, but at a smaller training/inference data number ratio of 1.5:1. Only a single training epoch is required during the learning process. Meanwhile, to the best of our knowledge, this is the highest accuracy among the non-backpropagation based SNNs. Finally, we conclude the few-shot learning (FSL) paradigm of the developed network: 1) a hierarchical structure-based network design involves prior human knowledge; 2) SNNs for content-based global dynamic feature detection.
Reference41 articles.
1. “A low power, fully event-based gesture recognition system,”;Amir;2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017,2017
2. Nengo: a python tool for building large-scale functional brain models;Bekolay;Front. Neuroinform,2014
3. Spike timing-dependent plasticity: a hebbian learning rule;Caporale;Ann. Rev. Neurosci,2008
4. Hierarchical graph neural networks for few-shot learning;Chen;IEEE Trans. Circ. Syst. Video Technol,2022
5. Language modeling using lmus: 10x better data efficiency or improved scaling compared to transformers;Chilkuri;CoRR,2021
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Reservoir Computing in Rehabilitation Video Analyses;2023 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM);2023-06-09