NLP学习参考
神经网络反向传播矩阵求导
https://zhuanlan.zhihu.com/p/83859554?from_voters_page=true
词嵌入向量WordEmbedding的原理和生成方法
https://www.sohu.com/a/210757729_826434
LSTM详解
https://blog.csdn.net/qian99/article/details/88628383
【神经网络】学习笔记十六——Attention机制
https://blog.csdn.net/zhuge2017302307/article/details/120025027
Attention用于NLP的一些小结
https://zhuanlan.zhihu.com/p/35739040
深度学习之GRU网络
A tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the "echo state network" approach
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.378.4095&rep=rep1&type=pdf