Do not use " in keypoints

episodes/1-introduction.Rmd

@@ -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/3-monitor-the-model.Rmd

@@ -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

@@ -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

@@ -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
 :::