期刊
NEURAL NETWORKS
卷 154, 期 -, 页码 543-559出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2022.07.010
关键词
Spatiotemporal feature descriptor; Spike -based learning; Event streams classification; Spiking neural network
资金
- National Key Research and Development Program of China [2020AAA0105900]
- NSAF [U2030204]
- Zhejiang Lab [2021KC0AC01]
This paper proposes a novel event descriptor and a local-search based multi-spike learning algorithm for encoding and learning the spatiotemporal information of event streams, achieving superior performance in classification tasks.
Event cameras sense changes in light intensity and record them as an asynchronous event stream. Efficiently encoding and learning spatiotemporal information of the event streams remain challenging. In this paper, we propose a novel event descriptor to encode the spatio-temporal features for event streams and a local-search based multi-spike learning algorithm for spiking neural networks to classify encoded features. The spatio-temporal event surface (STES) descriptor explicitly captures both spatial and temporal correlations among events, and thus can characterize spatiotemporal features more accurately than existing feature descriptors that focus only on temporal or spatial information. In classification with multi-spike learning, we introduce a local search and gradient clipping mechanism to ensure the efficiency and stability of learning, which avoids other multi-spike learning rules' time-consuming global search and the gradient explosion problem. Experimental results demonstrate the superior classification performance of our proposed model, especially for event streams with rich spatiotemporal dynamics. (C) 2022 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据