arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.10061cs.LGstat.ML
收藏

Omni-Scale CNN:用于时间序列分类的简单有效的内核大小配置

Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

Australian Artificial Intelligence Institute(澳大利亚人工智能研究所);University of Technology Sydney(悉尼科技大学);Google(谷歌);University of Washington(华盛顿大学);University of Maryland, College Park(马里兰大学帕克分校)

Wensi Tang, Guodong Long, Lu Liu, Tianyi Zhou, Michael Blumenstein, Jing Jiang

摘要:

接收场(RF)的大小一直是一维卷积神经网络(1D-CNN)在时间序列分类任务中最重要的因素之一。人们已经做出了很大的努力来选择合适的大小,因为它对性能有很大的影响,并且对于每个数据集都有很大的不同。在本文中,我们提出了一个用于1D-CNN的Omni-Scale块(OS块),其中内核大小由一个简单而通用的规则决定。特别地,它是一组内核大小,可以通过根据时间序列的长度由多个素数组成来有效地覆盖不同数据集的最佳RF大小。实验结果表明,具有OS块的模型可以实现与具有搜索到的最佳RF大小的模型相似的性能,并且由于强大的最佳RF大小捕获能力,具有OS块的简单1D-CNN模型在四个时间序列基准上实现了最先进的性能,包括来自多个域的单变量和多变量数据。全面的分析和讨论揭示了为什么OS块可以在不同的数据集上捕获最佳的RF大小。代码可用[https://github.com/Wensi-Tang/OS-CNN]

英文摘要:

The Receptive Field (RF) size has been one of the most important factors for One Dimensional Convolutional Neural Networks (1D-CNNs) on time series classification tasks. Large efforts have been taken to choose the appropriate size because it has a huge influence on the performance and differs significantly for each dataset. In this paper, we propose an Omni-Scale block (OS-block) for 1D-CNNs, where the kernel sizes are decided by a simple and universal rule. Particularly, it is a set of kernel sizes that can efficiently cover the best RF size across different datasets via consisting of multiple prime numbers according to the length of the time series. The experiment result shows that models with the OS-block can achieve a similar performance as models with the searched optimal RF size and due to the strong optimal RF size capture ability, simple 1D-CNN models with OS-block achieves the state-of-the-art performance on four time series benchmarks, including both univariate and multivariate data from multiple domains. Comprehensive analysis and discussions shed light on why the OS-block can capture optimal RF sizes across different datasets. Code available [https://github.com/Wensi-Tang/OS-CNN]

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑