Incorporating Taylor Series and Recursive Structure in Neural Networks for Time Series Prediction
This work addresses time series analysis problems for fields like physics, biology, chemistry, and finance, but appears incremental as it builds on existing ResNet structures.
The paper tackled time series prediction by proposing a neural network architecture that integrates ResNet structures and a Taylor series framework, resulting in notable enhancements in test accuracy across baseline datasets, with further improvements from a recursive step.
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.