How to test a Restricted Boltzmann Machine implementation ?

Question

I developed a simple binary Restricted Boltzmann Machine implementation and now I would like to test it. (Ultimately I'm gonna use it for a DBN, but I would like to test independently).

I saw that several people and papers are talking about testing it MNIST dataset, but I didn't find details on how to do that.

Do I have to add a new classification layer connected to the hidden units and then use backpropagation to train it? Isn't there another way?

Some people are also plotting the weights (again in MNIST), but I have problems with how you can plot weight and what does that represent...

Thanks

Answer 1

The "Tracking Progress" part in the RBM tutorial at deeplearning.net (http://deeplearning.net/tutorial/rbm.html) gives very good direction like:

• Check that samples from the RBM look like the training data

• (For image data) Check that hidden variable values maxima look sort of like smooth Gabor filter banks

• Track the pseudolikelihood

If you wish to learn more about Machine Learning visit this Machine Learning Course.