[MUSIC] In this module we've
covered a lot of ground. To start with we motivated taking
a probabilistic model-based approach to clustering, and showed mixtures of Gaussians as
a special example of such an approach. Then we presented the Algorithm, which is
a very generally useful algorithm, and we specified it specifically for
mixtures of Gaussians. And throughout the module we've compared
and contrasted these model based approaches with the K-means algorithm
that we described in the last module. And what we saw in this module is
that you can actually view K-means as a special case of For
mixtures of Gaussians. So, thinking about
mixtures of Gaussians and In order to infer our cluster
parameters and our soft assignments, really is a generalization of the K-means
algorithm that we showed before. But there is a cost to it, because there
are a lot more parameters that we have to think about learning from data. And in addition, there's a computational
cost to doing Instead of K-means, both when we're computing
our responsibilities and when we're estimating
our model parameters. Each of these steps is more
intensive than the steps that you have to perform in K-means. So it is a trade-off in
terms of flexibility and the descriptive output you get. You get the soft assignments
capturing uncertainty and you can do different things with that,
but there is a cost to it. And in summary, I'll just leave you with a
list of things that you should be able to do having watched this module. [MUSIC]