From 37557acb0ff8d5d2f897f73706a5f8a102de94ea Mon Sep 17 00:00:00 2001 From: ShusenTang Date: Thu, 18 Apr 2019 23:53:39 +0800 Subject: [PATCH] fix bug --- README.md | 4 ++-- docs/chapter06_RNN/6.10_bi-rnn.md | 3 +-- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index ee6423b..1659159 100644 --- a/README.md +++ b/README.md @@ -63,8 +63,8 @@ Dive into Deep Learning with PyTorch code. [6.6 通过时间反向传播](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.6_bptt.md) [6.7 门控循环单元（GRU）](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.7_gru.md) [6.8 长短期记忆（LSTM）](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.8_lstm.md) -[6.9 深度循环神经网络¶](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.9_deep-rnn.md) -[6.10 双向循环神经网络¶](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.10_bi-rnn.md) +[6.9 深度循环神经网络](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.9_deep-rnn.md) +[6.10 双向循环神经网络](https://github.com/ShusenTang/Dive-into-DL-PyTorch/blob/master/docs/chapter06_RNN/6.10_bi-rnn.md) diff --git a/docs/chapter06_RNN/6.10_bi-rnn.md b/docs/chapter06_RNN/6.10_bi-rnn.md index 3ad21e4..fe68fc8 100644 --- a/docs/chapter06_RNN/6.10_bi-rnn.md +++ b/docs/chapter06_RNN/6.10_bi-rnn.md @@ -3,8 +3,7 @@ 之前介绍的循环神经网络模型都是假设当前时间步是由前面的较早时间步的序列决定的，因此它们都将信息通过隐藏状态从前往后传递。有时候，当前时间步也可能由后面时间步决定。例如，当我们写下一个句子时，可能会根据句子后面的词来修改句子前面的用词。双向循环神经网络通过增加从后往前传递信息的隐藏层来更灵活地处理这类信息。图6.12演示了一个含单隐藏层的双向循环神经网络的架构。
- +
图6.12 双向循环神经网络的架构
-- GitLab