Clustering
1 Unsupervised Learning: Introduction
This is going to be an exciting time because this is the first unsupervised learning algorithm we're learning. We are going to have the computer learn from unlabeled data instead of previously labeled data.
So, what is unsupervised learning? At the beginning of the course, I briefly introduced unsupervised learning. However, we still need to compare it with supervised learning.
In a typical supervised learning, we have a labeled training set, and our goal is to find a decision boundary that can distinguish between positive and negative samples. In supervised learning here, we have a series of labels, and we need to draw a combined into a hypothetical function. The difference is that in unsupervised learning, our data does not come with any labels. The data we get is like this:
Here we have a series of points, but no labels. Therefore, our training set can be written as only x (1) x^{(1)}