Variational Gaussian Mixtures for Face Detection
This article is originally published at http://jean9208.github.io/
A Gaussian mixture model is a probabilistic way of representing subpopulations within an overall population. We only observe the data, not the subpopulation from which observation belongs.
We have $N$ random variables observed, each distributed according to a mixture of K gaussian components. Each gaussian has its own parameters, and we should be able to estimate the category using Expectation Maximization, as we are using a latent variables model.
Now, in a bayesian scenario, each parameter of each gaussian is also a random variable, as well as the mixture weights. To estimate the distributions we use Variational...
Please visit source website for post related comments.