0
Attention is all you need
来自Google的一篇神经翻译的文章，在这篇文章中作者们抛弃了传统Encoder-Decoder中经典的卷积和循环结构，仅保留了attention的结构，在减少了训练成本的同时在数个数据集上取得了最优的BLEU.paper link
Archive: 2018/3
0
Attention is all you need
来自Google的一篇神经翻译的文章，在这篇文章中作者们抛弃了传统Encoder-Decoder中经典的卷积和循环结构，仅保留了attention的结构，在减少了训练成本的同时在数个数据集上取得了最优的BLEU.paper link
0
Tensorflow_Eager
Eager execution is a feature that makes TensorFlow execute operations immediately: concrete values are returned, instead of a computational graph to be executed later.
0
Advanced Architectures and Memory Networks
Model overview and combinations, Dynamic memory networks. CS224n lecture 16.