Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2402.06441 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909100170805248 |
|---|---|
| author | Mau, Jarrod Moon, Kevin |
| author_facet | Mau, Jarrod Moon, Kevin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_06441 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Incorporating Taylor Series and Recursive Structure in Neural Networks for Time Series Prediction Mau, Jarrod Moon, Kevin Machine Learning 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. |
| title | Incorporating Taylor Series and Recursive Structure in Neural Networks for Time Series Prediction |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.06441 |