Machine learningTime-series forecasting
SegRNN：用于长期时间序列预测的段循环神经网络
SegRNN 是由 Shengsheng Lin 等人于 2023 年提出的一种用于长期时间序列预测的循环神经网络架构。它不按时间步处理，而是将输入序列划分为固定长度的段，并将每个段作为一个单一 token 输入到 GRU 中。这种基于段的设计大大减少了循环迭代次数，解决了 RNN 在对许多单个时间步上的非常长的依赖关系进行建模时面临的众所周知的问题。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Lin, S., Lin, W., Wu, W., Zhao, F., Mo, R., & Zhang, H. (2023). SegRNN: Segment recurrent neural network for long-term time series forecasting. arXiv preprint. link ↗
如何引用本页
ScholarGate. (2026, June 2). SegRNN (Segment Recurrent Neural Network). ScholarGate. https://scholargate.app/zh/deep-learning/segrnn
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →