One of the famous feature extraction techniques is Principal Component analysis or PCA. We will first start with the intuition behind the PCA technique. After that, we will move to dive a bit in the mathematical model behind it. Then, we will discuss how much dimensions can we reduce and how much this reduction affects the dataset information that we have.

After studying this subsection, you should be able to:

• Explain the intuition behind feature extraction 
• Explain the steps of the PCA dimensionality reduction technique 
• Use a scree plot to define the optimal number of principal components 
• Calculate the exact variance retained after applying PCA dimensionality reduction