I am trying to learn machine learning concepts through online materials. I just studied tutorial on Expectation Maximisation algorithm. I thought one numerical example can make better understanding. Here I need your help to solve a problem:

Let, we have data points points: 𝑥1=2, 𝑥2=3, 𝑥3 = 4, 𝑥4=12, 𝑥5=13, 𝑥6=14, 𝑥7=15, 𝑥8=16, and an initial clustering 𝐶1= {𝑥1, 𝑥2, 𝑥3, 𝑥4, 𝑥5} and 𝐶2 = {𝑥6, 𝑥7, 𝑥8}.

We can compute initialization $\Theta$ for EM from sample mean, covariance and relative frequency.

But my question is, how can I compute probability that these points have been generated by the model with parameters $\Theta$, i.e. $𝑝(X|\Theta)$?

  • 1
    $\begingroup$ A reference to that tutorial might be helpful. $\endgroup$ – Juho Kokkala Nov 26 '14 at 14:08
  • 1
    $\begingroup$ Defining a model would make your question clearer. As stated it does not directly relate to EM. $\endgroup$ – Xi'an Nov 26 '14 at 18:03

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.