Merge pull request #444 from carpentries-incubator/small-fixes-review

Small fixes from Carpentries Lab review

episodes/1-introduction.Rmd

@@ -1,30 +1,30 @@
 ---
 title: 'Introduction'
-teaching: 40
-exercises: 15
+teaching: 50
+exercises: 30
 ---
 
 :::::::::::::::::::::::::::::::::::::: questions
 
-- "What is Deep Learning?"
-- "When does it make sense to use and not use Deep Learning?"
-- "When is it successful?"
-- "What are the tools involved?"
-- "What is the workflow for Deep Learning?"
-- "Why did we choose to use Keras in this lesson?"
-- "How do neural networks learn?"
+- What is Deep Learning?
+- When does it make sense to use and not use Deep Learning?
+- When is it successful?
+- What are the tools involved?
+- What is the workflow for Deep Learning?
+- Why did we choose to use Keras in this lesson?
+- How do neural networks learn?
 
 ::::::::::::::::::::::::::::::::::::::::::::::::
 
 :::::::::::::::::::::::::::::::::::::: objectives
 
-- "Recall the sort of problems for which Deep Learning is a useful tool"
-- "List some of the available tools for Deep Learning"
-- "Recall the steps of a Deep Learning workflow"
-- "Identify the inputs and outputs of a deep neural network."
-- "Explain the operations performed in a single neuron"
-- "Test that you have correctly installed the Keras, Seaborn and Sklearn libraries"
-- "Describe what a loss function is"
+- Recall the sort of problems for which Deep Learning is a useful tool
+- List some of the available tools for Deep Learning
+- Recall the steps of a Deep Learning workflow
+- Identify the inputs and outputs of a deep neural network.
+- Explain the operations performed in a single neuron
+- Test that you have correctly installed the Keras, Seaborn and Sklearn libraries
+- Describe what a loss function is
 
 ::::::::::::::::::::::::::::::::::::::::::::::::
 
@@ -217,7 +217,7 @@ A more complicated and less used loss function for regression is the [Huber loss
 Below you see the Huber loss (green, delta = 1) and Squared error loss (blue)
 as a function of `y_true - y_pred`.
 
-![](fig/01_huber_loss.png){alt='Line plot comparing squared error loss function with the Huber loss function where delta = 1, showing the cost of prediction error of both functions equal where y_true - y_pred is between -1 and 1, then rising linearly with the Huber loss function as y_true diverges further from y_pred, as opposed to expontentially for the squared error function.',' width='400px'}
+![](fig/01_huber_loss.png){alt='Line plot comparing squared error loss function with the Huber loss function where delta = 1, showing the cost of prediction error of both functions equal where y_true - y_pred is between -1 and 1, then rising linearly with the Huber loss function as y_true diverges further from y_pred, as opposed to expontentially for the squared error function.' width='400px'}
 
 Which loss function is more sensitive to outliers?
 
@@ -461,13 +461,13 @@ You should get a version number reported. At the time of writing 1.2.2 is the la
 
 :::::::::::::::::::::::::::::::::::::: keypoints
 
-- "Machine learning is the process where computers learn to recognise patterns of data."
-- "Artificial neural networks are a machine learning technique based on a model inspired by groups of neurons in the brain."
-- "Artificial neural networks can be trained on example data."
-- "Deep Learning is a machine learning technique based on using many artificial neurons arranged in layers."
-- "Neural networks learn by minimizing a loss function."
-- "Deep Learning is well suited to classification and prediction problems such as image recognition."
-- "To use Deep Learning effectively we need to go through a workflow of: defining the problem, identifying inputs and outputs, preparing data, choosing the type of network, choosing a loss function, training the model, refine the model, measuring performance before we can classify data."
-- "Keras is a Deep Learning library that is easier to use than many of the alternatives such as TensorFlow and PyTorch."
+- Machine learning is the process where computers learn to recognise patterns of data.
+- Artificial neural networks are a machine learning technique based on a model inspired by groups of neurons in the brain.
+- Artificial neural networks can be trained on example data.
+- Deep Learning is a machine learning technique based on using many artificial neurons arranged in layers.
+- Neural networks learn by minimizing a loss function.
+- Deep Learning is well suited to classification and prediction problems such as image recognition.
+- To use Deep Learning effectively we need to go through a workflow of: defining the problem, identifying inputs and outputs, preparing data, choosing the type of network, choosing a loss function, training the model, refine the model, measuring performance before we can classify data.
+- Keras is a Deep Learning library that is easier to use than many of the alternatives such as TensorFlow and PyTorch.
 
 ::::::::::::::::::::::::::::::::::::::::::::::::

episodes/2-keras.Rmd

@@ -5,22 +5,22 @@ exercises: 50
 ---
 
 ::: questions
-- "What is a neural network?"
-- "How do I compose a Neural Network using Keras?"
-- "How do I train this network on a dataset?"
-- "How do I get insight into learning process?"
-- "How do I measure the performance of the network?"
+- What is a neural network?
+- How do I compose a Neural Network using Keras?
+- How do I train this network on a dataset?
+- How do I get insight into learning process?
+- How do I measure the performance of the network?
 :::
 
 ::: objectives
-- "Use the deep learning workflow to structure the notebook"
-- "Explore the dataset using pandas and seaborn"
-- "Use one-hot encoding to prepare data for classification in Keras"
-- "Describe a fully connected layer"
-- "Implement a fully connected layer with Keras"
-- "Use Keras to train a small fully connected network on prepared data"
-- "Interpret the loss curve of the training process"
-- "Use a confusion matrix to measure the trained networks' performance on a test set"
+- Use the deep learning workflow to structure the notebook
+- Explore the dataset using pandas and seaborn
+- Use one-hot encoding to prepare data for classification in Keras
+- Describe a fully connected layer
+- Implement a fully connected layer with Keras
+- Use Keras to train a small fully connected network on prepared data
+- Interpret the loss curve of the training process
+- Use a confusion matrix to measure the trained networks' performance on a test set
 :::
 
 

episodes/3-monitor-the-model.Rmd

@@ -5,22 +5,22 @@ exercises: 80
 ---
 
 ::: questions
-- "How do I create a neural network for a regression task?"
-- "How does optimization work?"
-- "How do I monitor the training process?"
-- "How do I detect (and avoid) overfitting?"
-- "What are common options to improve the model performance?"
+- How do I create a neural network for a regression task?
+- How does optimization work?
+- How do I monitor the training process?
+- How do I detect (and avoid) overfitting?
+- What are common options to improve the model performance?
 :::
 
 ::: objectives
-- "Explain the importance of keeping your test set clean, by validating on the validation set instead of the test set"
-- "Use the data splits to plot the training process"
-- "Explain how optimization works"
-- "Design a neural network for a regression task"
-- "Measure the performance of your deep neural network"
-- "Interpret the training plots to recognize overfitting"
-- "Use normalization as preparation step for Deep Learning"
-- "Implement basic strategies to prevent overfitting"
+- Explain the importance of keeping your test set clean, by validating on the validation set instead of the test set
+- Use the data splits to plot the training process
+- Explain how optimization works
+- Design a neural network for a regression task
+- Measure the performance of your deep neural network
+- Interpret the training plots to recognize overfitting
+- Use normalization as preparation step for Deep Learning
+- Implement basic strategies to prevent overfitting
 :::
 
 ::: instructor
@@ -990,6 +990,6 @@ This will turn the data into time series data which in turn might also make it w
 
 
 ::: keypoints
-- "Separate training, validation, and test sets allows monitoring and evaluating your model."
-- "Batchnormalization scales the data as part of the model."
+- Separate training, validation, and test sets allows monitoring and evaluating your model.
+- Batchnormalization scales the data as part of the model.
 :::

episodes/4-advanced-layer-types.Rmd

@@ -5,16 +5,16 @@ exercises: 70
 ---
 
 ::: questions
-- "Why do we need different types of layers?"
-- "What are good network designs for image data?"
-- "What is a convolutional layer?"
-- "How can we use different types of layers to prevent overfitting?"
+- Why do we need different types of layers?
+- What are good network designs for image data?
+- What is a convolutional layer?
+- How can we use different types of layers to prevent overfitting?
 :::
 
 ::: objectives
-- "Understand why convolutional and pooling layers are useful for image data"
-- "Implement a convolutional neural network on an image dataset"
-- "Use a drop-out layer to prevent overfitting"
+- Understand why convolutional and pooling layers are useful for image data
+- Implement a convolutional neural network on an image dataset
+- Use a drop-out layer to prevent overfitting
 :::
 
 
@@ -793,7 +793,7 @@ model.save('cnn_model')
 ```
 
 ::: keypoints
-- "Convolutional layers make efficient reuse of model parameters."
-- "Pooling layers decrease the resolution of your input"
-- "Dropout is a way to prevent overfitting"
+- Convolutional layers make efficient reuse of model parameters.
+- Pooling layers decrease the resolution of your input
+- Dropout is a way to prevent overfitting
 :::

episodes/5-outlook.Rmd

@@ -5,15 +5,15 @@ exercises: 15
 ---
 
 ::: questions
-- "How does what I learned in this course translate to real-world problems?"
-- "How do I organise a deep learning project?"
-- "What are next steps to take after this course?"
+- How does what I learned in this course translate to real-world problems?
+- How do I organise a deep learning project?
+- What are next steps to take after this course?
 :::
 
 ::: objectives
-- "Understand that what we learned in this course can be applied to real-world problems"
-- "Use best practices for organising a deep learning project"
-- "Identify next steps to take after this course"
+- Understand that what we learned in this course can be applied to real-world problems
+- Use best practices for organising a deep learning project
+- Identify next steps to take after this course
 :::
 
 You have come to the end of this course.
@@ -155,7 +155,7 @@ Tensorflow/Keras will automatically detect and use a GPU if it is available on y
 A simple and quick way to get access to a GPU is to use [Google Colab](https://colab.google/)
 
 ::: keypoints
-- "Although the data preparation and model architectures are somewhat more complex,
-what we have learned in this course can directly be applied to real-world problems"
-- "Use what you have learned in this course as a basis for your own learning trajectory in the world of deep learning"
+- Although the data preparation and model architectures are somewhat more complex,
+what we have learned in this course can directly be applied to real-world problems
+- Use what you have learned in this course as a basis for your own learning trajectory in the world of deep learning
 :::