afeng滴blog论文那些事儿
基础知识 Base
tanh，详解3
torch.gather函数详解4，见汤胤评论
深度学习 Deep Learning
Attention，详解9，视频10 11
Transformer，详解12
强化学习 Reinforcement Learning
SARSA，详解13
Q-Learning，详解14
DQN，详解15
参考资料 Reference
-
https://www.jianshu.com/p/037bf733713f “简书: 分类问题中Sigmoid与Softmax区别” ↩︎
-
https://devpress.csdn.net/xian/64a6246db1e197348be16c6a.html “论坛: 三分钟认知Softmax和Sigmoid的详细区别” ↩︎
-
https://www.jianshu.com/p/7409c8f1cdca “简书: 神经网络中的激活函数-tanh” ↩︎
-
https://zhuanlan.zhihu.com/p/352877584 “知乎: 图解PyTorch中的torch.gather函数” ↩︎
-
https://zhuanlan.zhihu.com/p/32085405 “知乎: 人人都能看懂的LSTM” ↩︎
-
https://zhuanlan.zhihu.com/p/42717426 “知乎: 详解LSTM” ↩︎
-
https://zhuanlan.zhihu.com/p/32481747 “知乎: 人人都能看懂的GRU” ↩︎
-
https://arxiv.org/pdf/1412.3555.pdf “论文: Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling” ↩︎
-
https://zhuanlan.zhihu.com/p/46313756 “知乎: Attention机制简单总结” ↩︎
-
https://www.bilibili.com/video/BV1q3411U7Hi “Bili: Attention、Transformer公式推导和矩阵变化” ↩︎
-
https://zhuanlan.zhihu.com/p/46313756 “知乎: Attention机制简单总结” ↩︎
-
https://zhuanlan.zhihu.com/p/166608727 “知乎: 举个例子讲下transformer的输入输出细节及其他” ↩︎
-
./RL/common_alg/SARSA.md “文档: SARSA” ↩︎
-
./RL/common_alg/Q-Learning.md “文档: Q-Learning” ↩︎
-
https://paddlepedia.readthedocs.io/en/latest/tutorials/reinforcement_learning/DQN.html “文档: DQN” ↩︎