Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
时间: 2024-04-24 18:25:05 浏览: 395
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting是一篇2021年发表在AAAI会议上的论文,它提出了一种名为Informer的方法,用于解决长时间序列预测的问题。\[2\]这篇论文的目标是在长时间序列预测中提高预测能力并提高效率。传统的Transformer方法在长时间序列预测上存在一些局限性,而Informer通过引入一些新的机制来克服这些局限性。\[3\]具体来说,Informer采用了一种多层次的注意力机制,以便更好地捕捉长时间序列中的依赖关系,并引入了一种自适应长度的编码器和解码器,以提高对长序列的建模能力。通过这些改进,Informer在长时间序列预测任务上取得了更好的效果。
#### 引用[.reference_title]
- *1* *3* [Informer: Beyond Efficient Transformer for Long SequenceTime-Series Forecasting](https://blog.csdn.net/lwera/article/details/127389652)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^control_2,239^v3^insert_chatgpt"}} ] [.reference_item]
- *2* [Informer:超越Transformer的长时间序列预测模型](https://blog.csdn.net/zuiyishihefang/article/details/123437169)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^control_2,239^v3^insert_chatgpt"}} ] [.reference_item]
[ .reference_list ]
阅读全文