Autoformer
时间: 2023-12-14 08:04:09 浏览: 95
AUTOFORM介绍
Autoformer是一种基于Transformer结构的时序预测模型,它在Self-attention的改进上进行了创新。与之前的模型不同,Autoformer更关注将Self-attention应用于时序计算,并设计了更适合时序分析的attention结构。它是Transformer的升级版本,针对时间序列问题进行了一系列优化。模型的核心结构包括Series Decomposition Block模块和对多头注意力机制的升级AutoCorrelationMechanism。如果想详细了解Autoformer的细节,可以参考杰少的相关文章,其中对Autoformer进行了全面深入的整理。
#### 引用[.reference_title]
- *1* *2* [Autoformer算法与代码分析](https://blog.csdn.net/buchuankuzi_/article/details/128390246)[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^insertT0,239^v3^insert_chatgpt"}} ] [.reference_item]
- *3* [Transformer在时序预测的应⽤第一弹——Autoformer](https://blog.csdn.net/m0_46413065/article/details/129658692)[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^insertT0,239^v3^insert_chatgpt"}} ] [.reference_item]
[ .reference_list ]
阅读全文