论文标题
使用尖峰神经网络的多元时间序列分类
Multivariate Time Series Classification Using Spiking Neural Networks
论文作者
论文摘要
在能源限制的方案（例如嵌入式设备）中，对时间数据流的需求越来越大，这是由物联网（IoT）和网络物理系统（CPS）的进步和扩展所驱动的。尖峰神经网络引起了人们的注意，因为它可以通过将信息编码和处理信息作为稀疏的尖峰事件来实现低功耗，这可以用于事件驱动的计算。最近的作品还显示了SNNS处理空间时间信息的能力。可以通过功率限制设备来利用此类优势来处理实时传感器数据。但是，大多数现有的SNN培训算法都集中在视力任务上，并且未解决时间信用分配。此外，编码的广泛采用的速率忽略了时间信息，因此不适合表示时间序列。在这项工作中，我们提出了一个编码方案，将时间序列转换为稀疏的空间时间尖峰模式。还提出了一种对空间时间模式进行分类的训练算法。在UCR存储库中的多个时间序列数据集上评估了建议的方法，并实现了与深神经网络相当的性能。
There is an increasing demand to process streams of temporal data in energy-limited scenarios such as embedded devices, driven by the advancement and expansion of Internet of Things (IoT) and Cyber-Physical Systems (CPS). Spiking neural network has drawn attention as it enables low power consumption by encoding and processing information as sparse spike events, which can be exploited for event-driven computation. Recent works also show SNNs' capability to process spatial temporal information. Such advantages can be exploited by power-limited devices to process real-time sensor data. However, most existing SNN training algorithms focus on vision tasks and temporal credit assignment is not addressed. Furthermore, widely adopted rate encoding ignores temporal information, hence it's not suitable for representing time series. In this work, we present an encoding scheme to convert time series into sparse spatial temporal spike patterns. A training algorithm to classify spatial temporal patterns is also proposed. Proposed approach is evaluated on multiple time series datasets in the UCR repository and achieved performance comparable to deep neural networks.
