feat(curriculum): add python multiple choice questions (#38890)

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

@@ -15,12 +15,14 @@ videoId: bejQ-W9BGJg
 
 ```yml
 question:
-  text: Question
+  text: How should you assign weights to input neurons before training your network for the first time?
+  
   answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - From smallest to largest.
+    - Completely randomly.
+    - Alphabetically.
+    - None of the above.
+  solution: 2
 ```
 
 </section>

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

@@ -15,12 +15,13 @@ videoId: Y5M7KH4A4n4
 
 ```yml
 question:
-  text: Question
+  text: When are Convolutional Neural Networks not useful?
+
   answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - 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.
+    - If your data is made up of different 2D or 3D images.
+    - If your data is text or sound based.
+  solution: 1
 ```
 
 </section>

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

@@ -15,12 +15,13 @@ videoId: zvalnHWGtx4
 
 ```yml
 question:
-  text: Question
+  text: Why is it better to calculate the gradient (slope) directly rather than numerically?
+
   answers:
-    - one
-    - two
-    - three
-  solution: 3
+    - It is computationally expensive to go back through the entire neural network and adjust the weights for each layer of the neural network.
+    - It is more accurate.
+    - There is no difference between the two methods.
+  solution: 1
 ```
 
 </section>

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

@@ -15,11 +15,13 @@ videoId: UVimlsy9eW0
 
 ```yml
 question:
-  text: Question
+  text: |
+    What are the main neural network components that make up a Long Short Term Memory network?
+
   answers:
-    - one
-    - two
-    - three
+    - New information and prediction.
+    - Prediction, collected possibilities, and selection.
+    - Prediction, ignoring, forgetting, and selection.
   solution: 3
 ```