gaspersic/freeCodeCamp
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

chore(learn): Applied MDX format to Chinese curriculum files (#40462)

Browse Source
This commit is contained in:
Randell Dawson
2020-12-16 00:37:30 -07:00
committed by GitHub
parent 873fce02a2
commit 9ce4a02a41
1665 changed files with 58741 additions and 88042 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/conclusion.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: LMNub5frQi4
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Most people that are experts in AI or machine learning usually...:
<section id='tests'>
## --answers--
```yml
question:
text: |
Most people that are experts in AI or machine learning usually...:
answers:
- |
have one specialization.
- |
have many specializations.
- |
have a deep understanding of many different frameworks.
solution: 1
```
have one specialization.
---
have many specializations.
---
have a deep understanding of many different frameworks.
## --video-solution--
1
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/convolutional-neural-networks-evaluating-the-model.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: eCATNvwraXg
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What is **not** a good way to increase the accuracy of a convolutional neural network?
<section id='tests'>
## --answers--
```yml
question:
text: |
What is **not** a good way to increase the accuracy of a convolutional neural network?
answers:
- |
Augmenting the data you already have.
- |
Using a pre-trained model.
- |
Using your test data to retrain the model.
solution: 3
```
Augmenting the data you already have.
---
Using a pre-trained model.
---
Using your test data to retrain the model.
## --video-solution--
3
# --hints--
# --solutions--
</section>

77
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/convolutional-neural-networks-picking-a-pretrained-model.md
View File

@ -4,46 +4,49 @@ challengeType: 11
videoId: h1XUt1AgIOI
---
## Description
<section id='description'>
</section>
# --question--
## Tests
<section id='tests'>
## --text--
```yml
question:
text: |
Fill in the blanks below to use Google's pre-trained MobileNet V2 model as a base for a convolutional neural network:
Fill in the blanks below to use Google's pre-trained MobileNet V2 model as a base for a convolutional neural network:
```py
base_model = tf.__A__.applications.__B__(input_shape=(160, 160, 3),
include_top=__C__,
weights='imagenet'
)
```
answers:
- |
A: `keras`
B: `MobileNetV2`
C: `False`
- |
A: `Keras`
B: `MobileNetV2`
C: `True`
- |
A: `keras`
B: `mobile_net_v2`
C: `False`
solution: 1
```py
base_model = tf.__A__.applications.__B__(input_shape=(160, 160, 3),
include_top=__C__,
weights='imagenet'
)
```
</section>
## --answers--
A: `keras`
B: `MobileNetV2`
C: `False`
---
A: `Keras`
B: `MobileNetV2`
C: `True`
---
A: `keras`
B: `mobile_net_v2`
C: `False`
## --video-solution--
1
# --hints--
# --solutions--

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/convolutional-neural-networks-the-convolutional-layer.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: LrdmcQpTyLw
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What are the three main properties of each convolutional layer?
<section id='tests'>
## --answers--
```yml
question:
text: |
What are the three main properties of each convolutional layer?
answers:
- |
Input size, the number of filters, and the sample size of the filters.
- |
Input size, input dimensions, and the color values of the input.
- |
Input size, input padding, and stride.
solution: 1
```
Input size, the number of filters, and the sample size of the filters.
---
Input size, input dimensions, and the color values of the input.
---
Input size, input padding, and stride.
## --video-solution--
1
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/convolutional-neural-networks.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: _1kTP7uoU9E
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Dense neural networks analyze input on a global scale and recognize patterns in specific areas. Convolutional neural networks...:
<section id='tests'>
## --answers--
```yml
question:
text: |
Dense neural networks analyze input on a global scale and recognize patterns in specific areas. Convolutional neural networks...:
answers:
- |
also analyze input globally and extract features from specific areas.
- |
do not work well for image classification or object detection.
- |
scan through the entire input a little at a time and learn local patterns.
solution: 3
```
also analyze input globally and extract features from specific areas.
---
do not work well for image classification or object detection.
---
scan through the entire input a little at a time and learn local patterns.
## --video-solution--
3
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/core-learning-algorithms-building-the-model.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: 5wHw8BTd2ZQ
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What kind of estimator/model does TensorFlow recommend using for classification?
<section id='tests'>
## --answers--
```yml
question:
text: |
What kind of estimator/model does TensorFlow recommend using for classification?
answers:
- |
`LinearClassifier`
- |
`DNNClassifier`
- |
`BoostedTreesClassifier`
solution: 2
```
`LinearClassifier`
---
`DNNClassifier`
---
`BoostedTreesClassifier`
## --video-solution--
2
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/core-learning-algorithms-classification.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: qFF7ZQNvK9E
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What is classification?
<section id='tests'>
## --answers--
```yml
question:
text: |
What is classification?
answers:
- |
The process of separating data points into different classes.
- |
Predicting a numeric value or forecast based on independent and dependent variables.
- |
None of the above.
solution: 1
```
The process of separating data points into different classes.
---
Predicting a numeric value or forecast based on independent and dependent variables.
---
None of the above.
## --video-solution--
1
# --hints--
# --solutions--
</section>

53
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/core-learning-algorithms-clustering.md
View File

@ -4,31 +4,38 @@ challengeType: 11
videoId: 8sqIaHc9Cz4
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Which of the following steps is **not** part of the K-Means algorithm?
<section id='tests'>
## --answers--
```yml
question:
text: |
Which of the following steps is **not** part of the K-Means algorithm?
answers:
- |
Randomly pick K points to place K centeroids.
- |
Assign each K point to the closest K centeroid.
- |
Move each K centeroid into the middle of all of their data points.
- |
Shuffle the K points so they're redistributed randomly.
- |
Reassign each K point to the closest K centeroid.
solution: 4
```
Randomly pick K points to place K centeroids.
---
Assign each K point to the closest K centeroid.
---
Move each K centeroid into the middle of all of their data points.
---
Shuffle the K points so they're redistributed randomly.
---
Reassign each K point to the closest K centeroid.
## --video-solution--
4
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/core-learning-algorithms-hidden-markov-models.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: IZg24y4wEPY
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What makes a Hidden Markov model different than linear regression or classification?
<section id='tests'>
## --answers--
```yml
question:
text: |
What makes a Hidden Markov model different than linear regression or classification?
answers:
- |
It uses probability distributions to predict future events or states.
- |
It analyzes the relationship between independent and dependent variables to make predictions.
- |
It separates data points into separate categories.
solution: 1
```
It uses probability distributions to predict future events or states.
---
It analyzes the relationship between independent and dependent variables to make predictions.
---
It separates data points into separate categories.
## --video-solution--
1
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/core-learning-algorithms-the-training-process.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: _cEwvqVoBhI
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What are epochs?
<section id='tests'>
## --answers--
```yml
question:
text: |
What are epochs?
answers:
- |
The number of times the model will see the same data.
- |
A type of graph.
- |
The number of elements you feed to the model at once.
solution: 1
```
The number of times the model will see the same data.
---
A type of graph.
---
The number of elements you feed to the model at once.
## --video-solution--
1
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/core-learning-algorithms-training-and-testing-data.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: wz9J1slsi7I
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What is categorical data?
<section id='tests'>
## --answers--
```yml
question:
text: |
What is categorical data?
answers:
- |
Another term for one-hot encoding.
- |
Any data that is not numeric.
- |
Any data that is represented numerically.
solution: 2
```
Another term for one-hot encoding.
---
Any data that is not numeric.
---
Any data that is represented numerically.
## --video-solution--
2
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/core-learning-algorithms-using-probabilities-to-make-predictions.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: fYAYvLUawnc
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What TensorFlow module should you import to implement `.HiddenMarkovModel()`?
<section id='tests'>
## --answers--
```yml
question:
text: |
What TensorFlow module should you import to implement `.HiddenMarkovModel()`?
answers:
- |
`tensorflow.keras`
- |
`tensorflow_gpu`
- |
`tensorflow_probability`
solution: 3
```
`tensorflow.keras`
---
`tensorflow_gpu`
---
`tensorflow_probability`
## --video-solution--
3
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/core-learning-algorithms-working-with-data.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: u85IOSsJsPI
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What does the pandas `.head()` function do?
<section id='tests'>
## --answers--
```yml
question:
text: |
What does the pandas `.head()` function do?
answers:
- |
Returns the number of entries in a data frame.
- |
Returns the number of columns in a data frame.
- |
By default, shows the first five rows or entries in a data frame.
solution: 3
```
Returns the number of entries in a data frame.
---
Returns the number of columns in a data frame.
---
By default, shows the first five rows or entries in a data frame.
## --video-solution--
3
# --hints--
# --solutions--
</section>

49
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/core-learning-algorithms.md
View File

@ -4,31 +4,36 @@ challengeType: 11
videoId: u5lZURgcWnU
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Which type of analysis would be best suited for the following problem?:
<section id='tests'>
You have the average temperature in the month of March for the last 100 years. Using this data, you want to predict the average temperature in the month of March 5 years from now.
```yml
question:
text: |
Which type of analysis would be best suited for the following problem?:
## --answers--
You have the average temperature in the month of March for the last 100 years. Using this data, you want to predict the average temperature in the month of March 5 years from now.
answers:
- |
Multiple regression
- |
Correlation
- |
Decision tree
- |
Linear regression
solution: 4
```
Multiple regression
---
Correlation
---
Decision tree
---
Linear regression
## --video-solution--
4
# --hints--
# --solutions--
</section>

83
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/creating-a-convolutional-neural-network.md
View File

@ -4,49 +4,52 @@ challengeType: 11
videoId: kfv0K8MtkIc
---
## Description
<section id='description'>
</section>
# --question--
## Tests
<section id='tests'>
## --text--
```yml
question:
text: |
Fill in the blanks below to complete the architecture for a convolutional neural network:
Fill in the blanks below to complete the architecture for a convolutional neural network:
```py
model = models.__A__()
model.add(layers.__B__(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(layers.__C__(2, 2))
model.add(layers.__B__(64, (3, 3), activation='relu'))
model.add(layers.__C__(2, 2))
model.add(layers.__B__(32, (3, 3), activation='relu'))
model.add(layers.__C__(2, 2))
```
answers:
- |
A: `Sequential`
B: `add`
C: `Wrapper`
- |
A: `keras`
B: `Cropping2D`
C: `AlphaDropout`
- |
A: `Sequential`
B: `Conv2D`
C: `MaxPooling2D`
solution: 3
```py
model = models.__A__()
model.add(layers.__B__(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(layers.__C__(2, 2))
model.add(layers.__B__(64, (3, 3), activation='relu'))
model.add(layers.__C__(2, 2))
model.add(layers.__B__(32, (3, 3), activation='relu'))
model.add(layers.__C__(2, 2))
```
</section>
## --answers--
A: `Sequential`
B: `add`
C: `Wrapper`
---
A: `keras`
B: `Cropping2D`
C: `AlphaDropout`
---
A: `Sequential`
B: `Conv2D`
C: `MaxPooling2D`
## --video-solution--
3
# --hints--
# --solutions--

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/introduction-machine-learning-fundamentals.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: KwL1qTR5MT8
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Which statement below is **false**?
<section id='tests'>
## --answers--
```yml
question:
text: |
Which statement below is **false**?
answers:
- |
Neural networks are modeled after the way the human brain works.
- |
Computer programs that play tic-tac-toe or chess against human players are examples of simple artificial intelligence.
- |
Machine learning is a subset of artificial intelligence.
solution: 1
```
Neural networks are modeled after the way the human brain works.
---
Computer programs that play tic-tac-toe or chess against human players are examples of simple artificial intelligence.
---
Machine learning is a subset of artificial intelligence.
## --video-solution--
1
# --hints--
# --solutions--
</section>

53
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/introduction-to-tensorflow.md
View File

@ -4,31 +4,38 @@ challengeType: 11
videoId: r9hRyGGjOgQ
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Which of the following is **not** a type of tensor?
<section id='tests'>
## --answers--
```yml
question:
text: |
Which of the following is **not** a type of tensor?
answers:
- |
Variable
- |
Flowing
- |
Placeholder
- |
SparseTensor
- |
Constant
solution: 2
```
Variable
---
Flowing
---
Placeholder
---
SparseTensor
---
Constant
## --video-solution--
2
# --hints--
# --solutions--
</section>

103
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-building-the-model.md
View File

@ -4,59 +4,62 @@ challengeType: 11
videoId: 32WBFS7lfsw
---
## Description
<section id='description'>
</section>
# --question--
## Tests
<section id='tests'>
## --text--
```yml
question:
text: |
Fill in the blanks below to complete the `build_model` function:
Fill in the blanks below to complete the `build_model` function:
```py
def build_mode(vocab_size, embedding_dim, rnn_units, batch_size):
model = tf.keras.Sequential([
tf.keras.layers.Embedding(vocab_size,
embedding_dim,
batch_input_shape=[batch_size, None]),
tf.keras.layers.__A__(rnn_units,
return_sequences=__B__,
recurrent_initializer='glorot_uniform),
tf.keras.layers.Dense(__C__)
])
__D__
```
answers:
- |
A: `ELU`
B: `True`
C: `vocab_size`
D: `return model`
- |
A: `LSTM`
B: `False`
C: `batch_size`
D: `return model`
- |
A: `LSTM`
B: `True`
C: `vocab_size`
D: `return model`
solution: 3
```py
def build_mode(vocab_size, embedding_dim, rnn_units, batch_size):
model = tf.keras.Sequential([
tf.keras.layers.Embedding(vocab_size,
embedding_dim,
batch_input_shape=[batch_size, None]),
tf.keras.layers.__A__(rnn_units,
return_sequences=__B__,
recurrent_initializer='glorot_uniform),
tf.keras.layers.Dense(__C__)
])
__D__
```
</section>
## --answers--
A: `ELU`
B: `True`
C: `vocab_size`
D: `return model`
---
A: `LSTM`
B: `False`
C: `batch_size`
D: `return model`
---
A: `LSTM`
B: `True`
C: `vocab_size`
D: `return model`
## --video-solution--
3
# --hints--
# --solutions--

59
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-create-a-play-generator.md
View File

@ -4,37 +4,40 @@ challengeType: 11
videoId: j5xsxjq_Xk8
---
## Description
<section id='description'>
</section>
# --question--
## Tests
<section id='tests'>
## --text--
```yml
question:
text: |
Fill in the blanks below to create the training examples for the RNN:
Fill in the blanks below to create the training examples for the RNN:
```py
char_dataset = tf.data.__A__.__B__(text_as_int)
```
answers:
- |
A: `DataSet`
B: `from_tensor_slices`
- |
A: `data`
B: `from_tensors`
- |
A: `DataSet`
B: `from_generator`
solution: 1
```py
char_dataset = tf.data.__A__.__B__(text_as_int)
```
</section>
## --answers--
A: `DataSet`
B: `from_tensor_slices`
---
A: `data`
B: `from_tensors`
---
A: `DataSet`
B: `from_generator`
## --video-solution--
1
# --hints--
# --solutions--

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-making-predictions.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: WO1hINnBj20
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Before you make a prediction with your own review, you should...:
<section id='tests'>
## --answers--
```yml
question:
text: |
Before you make a prediction with your own review, you should...:
answers:
- |
decode the training dataset and compare the results to the test data.
- |
use the encodings from the training dataset to encode your review.
- |
assign random values between 0 and the maximum number of vocabulary in your dataset to each word in your review.
solution: 2
```
decode the training dataset and compare the results to the test data.
---
use the encodings from the training dataset to encode your review.
---
assign random values between 0 and the maximum number of vocabulary in your dataset to each word in your review.
## --video-solution--
2
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-part-2.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: mUU9YXOFbZg
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Word embeddings are...:
<section id='tests'>
## --answers--
```yml
question:
text: |
Word embeddings are...:
answers:
- |
an unordered group of encoded words that describes the frequency of words in a given document.
- |
a group of encoded words that preserves the original order of the words in a given document.
- |
a vectorized representation of words in a given document that places words with similar meanings near each other.
solution: 3
```
an unordered group of encoded words that describes the frequency of words in a given document.
---
a group of encoded words that preserves the original order of the words in a given document.
---
a vectorized representation of words in a given document that places words with similar meanings near each other.
## --video-solution--
3
# --hints--
# --solutions--
</section>

47
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-recurring-neural-networks.md
View File

@ -4,29 +4,34 @@ challengeType: 11
videoId: bX5681NPOcA
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What is true about Recurrent Neural Networks?
<section id='tests'>
## --answers--
```yml
question:
text: |
What is true about Recurrent Neural Networks?
answers:
- |
1: They are a type of feed-forward neural network.
- |
2: They maintain an internal memory/state of the input that was already processed.
- |
3: RNN's contain a loop and process one piece of input at a time.
- |
4: Both 2 and 3.
solution: 4
```
1: They are a type of feed-forward neural network.
---
2: They maintain an internal memory/state of the input that was already processed.
---
3: RNN's contain a loop and process one piece of input at a time.
---
4: Both 2 and 3.
## --video-solution--
4
# --hints--
# --solutions--
</section>

79
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-sentimental-analysis.md
View File

@ -4,47 +4,50 @@ challengeType: 11
videoId: lYeLtu8Nq7c
---
## Description
<section id='description'>
</section>
# --question--
## Tests
<section id='tests'>
## --text--
```yml
question:
text: |
Fill in the blanks below to create the model for the RNN:
Fill in the blanks below to create the model for the RNN:
```py
model = __A__.keras.Sequential([
__A__.keras.layers.__B__(88584, 32),
__A__.keras.layers.__C__(32),
__A__.keras.layers.DENSE(1, activation='sigmoid')
])
```
answers:
- |
A: `tensor_flow`
B: `embedding`
C: `LSTM`
- |
A: `tf`
B: `Embedding`
C: `AlphaDropout`
- |
A: `tf`
B: `Embedding`
C: `LSTM`
solution: 3
```py
model = __A__.keras.Sequential([
__A__.keras.layers.__B__(88584, 32),
__A__.keras.layers.__C__(32),
__A__.keras.layers.DENSE(1, activation='sigmoid')
])
```
</section>
## --answers--
A: `tensor_flow`
B: `embedding`
C: `LSTM`
---
A: `tf`
B: `Embedding`
C: `AlphaDropout`
---
A: `tf`
B: `Embedding`
C: `LSTM`
## --video-solution--
3
# --hints--
# --solutions--

83
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns-training-the-model.md
View File

@ -4,51 +4,54 @@ challengeType: 11
videoId: hEUiK7j9UI8
---
## Description
<section id='description'>
</section>
# --question--
## Tests
<section id='tests'>
## --text--
```yml
question:
text: |
Fill in the blanks below to save your model's checkpoints in the `./checkpoints` directory and call the latest checkpoint for training:
Fill in the blanks below to save your model's checkpoints in the `./checkpoints` directory and call the latest checkpoint for training:
```py
checkpoint_dir = __A__
checkpoint_prefix = os.path.join(checkpoint_dir, 'ckpt_{epoch}')
```py
checkpoint_dir = __A__
checkpoint_prefix = os.path.join(checkpoint_dir, 'ckpt_{epoch}')
checkpoint_callback = tf.keras.callbacks.__B__(
filepath=checkpoint_prefix,
save_weights_only=True
)
checkpoint_callback = tf.keras.callbacks.__B__(
filepath=checkpoint_prefix,
save_weights_only=True
)
history = model.fit(data, epochs=2, callbacks=[__C__])
```
answers:
- |
A: `'./training_checkpoints'`
B: `ModelCheckpoint`
C: `checkpoint_prefix`
- |
A: `'./checkpoints'`
B: `ModelCheckpoint`
C: `checkpoint_callback`
- |
A: `'./checkpoints'`
B: `BaseLogger`
C: `checkpoint_callback`
solution: 2
history = model.fit(data, epochs=2, callbacks=[__C__])
```
</section>
## --answers--
A: `'./training_checkpoints'`
B: `ModelCheckpoint`
C: `checkpoint_prefix`
---
A: `'./checkpoints'`
B: `ModelCheckpoint`
C: `checkpoint_callback`
---
A: `'./checkpoints'`
B: `BaseLogger`
C: `checkpoint_callback`
## --video-solution--
2
# --hints--
# --solutions--

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/natural-language-processing-with-rnns.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: ZyCaF5S-lKg
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Natural Language Processing is a branch of artificial intelligence that...:
<section id='tests'>
## --answers--
```yml
question:
text: |
Natural Language Processing is a branch of artificial intelligence that...:
answers:
- |
deals with how computers understand and process natural/human languages.
- |
translates image data into natural/human languages.
- |
is focused on translating computer languages into natural/human languages.
solution: 1
```
deals with how computers understand and process natural/human languages.
---
translates image data into natural/human languages.
---
is focused on translating computer languages into natural/human languages.
## --video-solution--
1
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/neural-networks-activation-functions.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: S45tqW6BqRs
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
Which activation function switches values between -1 and 1?
<section id='tests'>
## --answers--
```yml
question:
text: |
Which activation function switches values between -1 and 1?
answers:
- |
ReLU (Rectified Linear Unit)
- |
Tanh (Hyperbolic Tangent)
- |
Sigmoid
solution: 2
```
ReLU (Rectified Linear Unit)
---
Tanh (Hyperbolic Tangent)
---
Sigmoid
## --video-solution--
2
# --hints--
# --solutions--
</section>

79
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/neural-networks-creating-a-model.md
View File

@ -4,47 +4,50 @@ challengeType: 11
videoId: K8bz1bmOCTw
---
## Description
<section id='description'>
</section>
# --question--
## Tests
<section id='tests'>
## --text--
```yml
question:
text: |
Fill in the blanks below to build a sequential model of dense layers:
Fill in the blanks below to build a sequential model of dense layers:
```py
model = __A__.__B__([
__A__.layers.Flatten(input_shape=(28, 28)),
__A__.layers.__C__(128, activation='relu'),
__A__.layers.__C__(10, activation='softmax')
])
```
answers:
- |
A: `keras`
B: `Sequential`
C: `Dense`
- |
A: `tf`
B: `Sequential`
C: `Categorical`
- |
A: `keras`
B: `sequential`
C: `dense`
solution: 1
```py
model = __A__.__B__([
__A__.layers.Flatten(input_shape=(28, 28)),
__A__.layers.__C__(128, activation='relu'),
__A__.layers.__C__(10, activation='softmax')
])
```
</section>
## --answers--
A: `keras`
B: `Sequential`
C: `Dense`
---
A: `tf`
B: `Sequential`
C: `Categorical`
---
A: `keras`
B: `sequential`
C: `dense`
## --video-solution--
1
# --hints--
# --solutions--

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/neural-networks-optimizers.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: hdOtRPQe1o4
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What is an optimizer function?
<section id='tests'>
## --answers--
```yml
question:
text: |
What is an optimizer function?
answers:
- |
A function that increases the accuracy of a model's predictions.
- |
A function that implements the gradient descent and backpropagation algorithms for you.
- |
A function that reduces the time a model needs to train.
solution: 2
```
A function that increases the accuracy of a model's predictions.
---
A function that implements the gradient descent and backpropagation algorithms for you.
---
A function that reduces the time a model needs to train.
## --video-solution--
2
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/neural-networks-with-tensorflow.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: uisdfrNrZW4
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
A densely connected neural network is one in which...:
<section id='tests'>
## --answers--
```yml
question:
text: |
A densely connected neural network is one in which...:
answers:
- |
all the neurons in the current layer are connected to one neuron in the previous layer.
- |
all the neurons in each layer are connected randomly.
- |
all the neurons in the current layer are connected to every neuron in the previous layer.
solution: 3
```
all the neurons in the current layer are connected to one neuron in the previous layer.
---
all the neurons in each layer are connected randomly.
---
all the neurons in the current layer are connected to every neuron in the previous layer.
## --video-solution--
3
# --hints--
# --solutions--
</section>

71
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/reinforcement-learning-with-q-learning-example.md
View File

@ -4,43 +4,46 @@ challengeType: 11
videoId: RBBSNta234s
---
## Description
<section id='description'>
</section>
# --question--
## Tests
<section id='tests'>
## --text--
```yml
question:
text: |
Fill in the blanks to complete the following Q-Learning equation:
Fill in the blanks to complete the following Q-Learning equation:
```py
Q[__A__, __B__] = Q[__A__, __B__] + LEARNING_RATE * (reward + GAMMA * np.max(Q[__C__, :]) - Q[__A__, __B__])
```
answers:
- |
A: `state`
B: `action`
C: `next_state`
- |
A: `state`
B: `action`
C: `prev_state`
- |
A: `state`
B: `reaction`
C: `next_state`
solution: 1
```py
Q[__A__, __B__] = Q[__A__, __B__] + LEARNING_RATE * (reward + GAMMA * np.max(Q[__C__, :]) - Q[__A__, __B__])
```
</section>
## --answers--
A: `state`
B: `action`
C: `next_state`
---
A: `state`
B: `action`
C: `prev_state`
---
A: `state`
B: `reaction`
C: `next_state`
## --video-solution--
1
# --hints--
# --solutions--

35
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/reinforcement-learning-with-q-learning-part-2.md
View File

@ -4,25 +4,26 @@ challengeType: 11
videoId: DX7hJuaUZ7o
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
What can happen if the agent does not have a good balance of taking random actions and using learned actions?
<section id='tests'>
## --answers--
```yml
question:
text: |
What can happen if the agent does not have a good balance of taking random actions and using learned actions?
answers:
- |
The agent will always try to minimize its reward for the current state/action, leading to local minima.
- |
The agent will always try to maximize its reward for the current state/action, leading to local maxima.
solution: 2
```
The agent will always try to minimize its reward for the current state/action, leading to local minima.
---
The agent will always try to maximize its reward for the current state/action, leading to local maxima.
## --video-solution--
2
# --hints--
# --solutions--
</section>

41
curriculum/challenges/chinese/11-machine-learning-with-python/tensorflow/reinforcement-learning-with-q-learning.md
View File

@ -4,27 +4,30 @@ challengeType: 11
videoId: Cf7DSU0gVb4
---
## Description
# --question--
<section id='description'>
</section>
## --text--
## Tests
The key components of reinforcement learning are...
<section id='tests'>
## --answers--
```yml
question:
text: |
The key components of reinforcement learning are...
answers:
- |
environment, representative, state, reaction, and reward.
- |
environment, agent, state, action, and reward.
- |
habitat, agent, state, action, and punishment.
solution: 2
```
environment, representative, state, reaction, and reward.
---
environment, agent, state, action, and reward.
---
habitat, agent, state, action, and punishment.
## --video-solution--
2
# --hints--
# --solutions--
</section>