Maximizing likelihood could not be used to the Gaussian mixture model directly, for its severe defects that we have come across at 'Maximum Likelihood of Gaussian Mixtures'. By the inspiration of K-means, a two-step algorithm was developed.
Original form K-Means algorithm might be one of the most accessible algorithms in machine learning. And many books and courses started with it. However, if we convert the task which K-means dealt with into a more mathematical form, there would be more interesting aspects coming to us.
We have discussed many machine learning algorithms, including linear regression, linear classification, neural network models and e.t.c, till now. However, most of them are supervised learning, which means a teacher is leading the models to bias to a certain task