提出新型周期激活函数LeakySineLU，提升时序分类性能。
Semi-Periodic Activation for Time Series Classification
- 设计兼具周期性与非线性的LeakySineLU激活函数。
- 在112个时序数据集上平均排名最优。
- 适合时序建模、神经网络优化研究者参考。
本文研究神经网络在时序任务中激活函数的不足，强调识别其关键特性以提升特定领域表现的必要性。通过系统分析有界性、单调性、非线性及周期性等性质，提出一种最大化覆盖这些特性的新激活函数——LeakySineLU。在112个基准时序分类数据集上，对常用激活函数进行实证评估，结果表明LeakySineLU在所有对比场景中均取得最佳平均排名。
原文摘要 · Abstract (English)
This paper investigates the lack of research on activation functions for neural network models in time series tasks. It highlights the need to identify essential properties of these activations to improve their effectiveness in specific domains. To this end, the study comprehensively analyzes properties, such as bounded, monotonic, nonlinearity, and periodicity, for activation in time series neural networks. We propose a new activation that maximizes the coverage of these properties, called LeakySineLU. We empirically evaluate the LeakySineLU against commonly used activations in the literature using 112 benchmark datasets for time series classification, obtaining the best average ranking in all comparative scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。