Detail Page

Unsupervised Learning

This lab session is aimed to provide a first introduction to unsupervised learning methods. In the first notebook, we'll study algorithms to perform clustering and dimensionality reduction (that is, k-means and principal component analysis (PCA)) In the second notebook, we'll apply these algorithms in a real-world dataset. Moreover, we'll cover a method to visualize high-dimensional data called t-SNE. We'll use three datasets during this lab session:

• a toy dataset to gain insight into how unsupervised learning algorithms work
• a research dataset to try out already-implemented algorithms and your own implementations!
• a real-world dataset to get a better understanding of the limitations these algorithms might have