Time series analysis is relevant in various disciplines such as physics, biology, chemistry, and finance. In this paper, we present a novel neural network architecture that integrates elements from ResNet structures, while introducing the innovative incorporation of the Taylor series framework. This approach demonstrates notable enhancements in test accuracy across many of the baseline datasets investigated. Furthermore, we extend our method to incorporate a recursive step, which leads to even further improvements in test accuracy. Our findings underscore the potential of our proposed model to significantly advance time series analysis methodologies, offering promising avenues for future research and application.

翻译：时间序列分析在物理学、生物学、化学和金融等多个学科中具有重要意义。本文提出了一种新型神经网络架构，该架构融合了ResNet结构中的要素，并创新性地引入了泰勒级数框架。这一方法在所研究的多个基准数据集上均展现出显著的测试精度提升。此外，我们对该方法进行了扩展，加入了递归步骤，从而进一步提升了测试精度。我们的研究结果凸显了所提出模型在推动时间序列分析方法论方面的巨大潜力，为未来的研究和应用开辟了有前景的途径。