weixin_44808865的博客

「ArXiv2020」【Efficient Transformers: A Survey】论文笔记Abstract1. Introduction2. Background on Transformers2.1 Multi-Head Self-AttentionOn the scalability of Self-Attention2.2 Position-wise Feed-forward Layers2.3 Putting it all together2.4 Transformer Mode3. A S

「AAAI2021_Best_Paper」【Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecast】论文笔记Abstract1. Introduction2. Preliminary3. Methodology4. Experiment5. ConclusionPaper：https://arxiv.org/abs/2012.07436v2Code：https://github.com/zhouhaoyi