|
I am working on continuous data(speech), and would like to build a deep belief network for classification purpose. I started with the matrbm library, but it doesn't have real-valued nodes. Is there any good library that allows to create DBNs with GB-RBMs? Also, I would like to get some idea on the physical interpretation of the model.
showing 5 of 6
show all
|
Integrate Charlie Tang's matlab code for Gaussian RBMs into your stuff: http://www.cs.toronto.edu/~tang/code/GaussianRBM.m
Thanks @osdf . Can you help me with a little more detail on how it works?
What do you want to know exactly? It is a GRBM that learns also the (conditional) variance for every visible unit (though the learned variance is independent of the setting of the hidden units). Details are described in http://www.cs.toronto.edu/~tang/papers/mr_dbn.pdf. Basically, the variances are determined via approximate maximum likelihood learning, exactly like the other parameters (weight, biases) are learned.
Thanks. I scaled the data to have zero-mean and unit-variance. And then trained a GRBM, followed by multiple layers of binary RBMs. I am not sure what I am doing wrong, but all values after the first layer comes as NaN. My GRBM implementation is here.
@osdf The problem got fixed after I reduced the learning rate by an order of magnitude.
@niharjyoti, it's an old post, but do you remember the range in which your GBRBM reconstruction error fell in? I'm trying to train after normalizing my data to unit variance, zero mean, but my error always stays above around 0.60...