It is often hard to see the relationship among machine learning methods. For example, one can view the popular k-means clustering algorithm as an instance of expectation maximization, which, again, can be viewed as a special case ariational inference.

Moreover when you learn a method such expectation maximization, or MCMC sampling methods, you can spend hours to understand the mathematics behind them. Yet, when it comes to implementation, it is not so clear how those formulas can be materialized into code.

This motivates me to write this blog to document my knowledge about machine learning methods, their relationship with each other, and, more importantly, their applications.