chore(i18n,chn): manually downloaded curriculum (#42858)

curriculum/challenges/chinese/11-machine-learning-with-python/how-neural-networks-work/deep-learning-demystified.md

@@ -1,6 +1,6 @@
 ---
 id: 5e9a0e9ef99a403d019610cc
-title: Deep Learning Demystified
+title: 解密深度学习
 challengeType: 11
 videoId: bejQ-W9BGJg
 dashedName: deep-learning-demystified
@@ -10,23 +10,23 @@ dashedName: deep-learning-demystified
 
 ## --text--
 
-How should you assign weights to input neurons before training your network for the first time?
+在你第一次训练你的网络之前，你应该如何给输入层节点分配权重？
 
 ## --answers--
 
-From smallest to largest.
+从小到大
 
 ---
 
-Completely randomly.
+完全随机的
 
 ---
 
-Alphabetically.
+按字母顺序
 
 ---
 
-None of the above.
+以上都不对
 
 ## --video-solution--
 

curriculum/challenges/chinese/11-machine-learning-with-python/how-neural-networks-work/how-convolutional-neural-networks-work.md

@@ -1,6 +1,6 @@
 ---
 id: 5e9a0e9ef99a403d019610cd
-title: How Convolutional Neural Networks work
+title: 卷积神经网络的工作原理
 challengeType: 11
 videoId: Y5M7KH4A4n4
 dashedName: how-convolutional-neural-networks-work
@@ -10,19 +10,19 @@ dashedName: how-convolutional-neural-networks-work
 
 ## --text--
 
-When are Convolutional Neural Networks not useful?
+卷积神经网络在什么时候是没有用的？
 
 ## --answers--
 
-If your data can't be made to look like an image, or if you can rearrange elements of your data and it's still just as useful.
+当数据的组成形式不能像图片存储的数据格式一样，或者说你的数据可以重新排列，它仍然可以被运用到卷积神经网络中。
 
 ---
 
-If your data is made up of different 2D or 3D images.
+如果你的数据是由 2D 或者 3D 图片组成的。
 
 ---
 
-If your data is text or sound based.
+如果你的数据是基于文本或者音频的形式。
 
 ## --video-solution--
 

curriculum/challenges/chinese/11-machine-learning-with-python/how-neural-networks-work/how-deep-neural-networks-work.md

@@ -1,6 +1,6 @@
 ---
 id: 5e9a0e9ef99a403d019610ca
-title: How Deep Neural Networks Work
+title: 深度神经网络的工作原理
 challengeType: 11
 videoId: zvalnHWGtx4
 dashedName: how-deep-neural-networks-work
@@ -10,19 +10,19 @@ dashedName: how-deep-neural-networks-work
 
 ## --text--
 
-Why is it better to calculate the gradient (slope) directly rather than numerically?
+相比较数字的计算，为什么深度神经网络可以更好地计算梯度（斜率）？
 
 ## --answers--
 
-It is computationally expensive to go back through the entire neural network and adjust the weights for each layer of the neural network.
+通过回溯整个神经网络来更改每一层神经网络的权重，在计算上来说是非常耗时的。
 
 ---
 
-It is more accurate.
+它更加准确。
 
 ---
 
-There is no difference between the two methods.
+这两种方法之间没有区别。
 
 ## --video-solution--
 

curriculum/challenges/chinese/11-machine-learning-with-python/how-neural-networks-work/recurrent-neural-networks-rnn-and-long-short-term-memory-lstm.md

@@ -1,6 +1,6 @@
 ---
 id: 5e9a0e9ef99a403d019610cb
-title: Recurrent Neural Networks RNN and Long Short Term Memory LSTM
+title: 循环神经网络 RNN 和长短期记忆 LSTM
 challengeType: 11
 videoId: UVimlsy9eW0
 dashedName: recurrent-neural-networks-rnn-and-long-short-term-memory-lstm
@@ -10,19 +10,19 @@ dashedName: recurrent-neural-networks-rnn-and-long-short-term-memory-lstm
 
 ## --text--
 
-What are the main neural network components that make up a Long Short Term Memory network?
+构成长短期记忆网络的主要神经网络组件是什么？
 
 ## --answers--
 
-New information and prediction.
+新的信息和预测
 
 ---
 
-Prediction, collected possibilities, and selection.
+预测、收集的可能性和选择
 
 ---
 
-Prediction, ignoring, forgetting, and selection.
+预测、忽视、遗忘和选择
 
 ## --video-solution--