In real world, data does not always come with labels and in such cases, we need to create our own clusters/labels in order to make some groupings in the data. This is called unsupervised learning. The following algorithms are used to do this:
There are a few other terms that are commonly associated with unsupervised learning as application areas.
The process of taking a sample of data and estimating the probability density function of a random variable is called density estimation. Once the distribution is learnt, one can generate samples that look like they are coming from the same distribution.
Underlying cause in the form of latent or missing variables can be figured out using the unsupervised learning techniques.
This topic is covered in depth, in a separate section of the book. Please refer to the index page for more details regarding the same.