Attention is all your need

Attention is all your need

整体架构：

encoder->decoder

从序列到序列：通过encoder获得序列映射到高维空间，并通过decoder输出序列

传统模型看这里：这里交代了序列模型的可视化动画

Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention) – Jay Alammar – Visualizing machine learning one concept at a time. (jalammar.github.io)

新模型：Transformer

构成：

1. encoder

   值得注意的是本文是由6个堆叠的也就是这样的