0
$\begingroup$

I am designing RBM with CD training methodology in MATLAB. CD is an unsupervised learning algorithm, so I do not need to use any label information included in input. Does that make sense?

$\endgroup$
1
$\begingroup$

Restricted Bolzmann Machine is one of the unsupervised learning method that finds latent feature for the input. If you want to use it as supervised way, you must add another softmax layer to the top layer of RBM in case of 1-of-K classification. You can do with CD as well.

$\endgroup$
  • $\begingroup$ Thanks. I understand it. i want to apply only unsupervised training. My question is that it means,unsupervised learning don't require any label information of an image? $\endgroup$ – subha Jun 24 '14 at 5:29
  • $\begingroup$ @subha You're right, you don't need any label information to perform CD and learn features with a RBM. $\endgroup$ – Baptiste Wicht Jul 4 '14 at 14:34
1
$\begingroup$

You do not require any of label information if you want use it as unsupervised way. However, if you want to get generative sampling number of MNIST dataset you have to put softmax layer, which means you need labels.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.