Thanks a lot for enhancing our understanding with this well commented code. I have a query regarding the sparsity constraint imposed in RBM, i.e in the pretrainRBM function. In order to update the hidden biases according to the sparsity constraint, why have you multiplied the gradients with 2.
dsW = dsW + SparseLambda * 2.0 * bsxfun(@times, (SparseQ-mH)', svdH)';
dsB = dsB + SparseLambda * 2.0 * (SparseQ-mH) .* sdH;
This does not match any update equation given by Lee et al. Could you please elaborate on this? Many thanks!
05 Mar 2014
Creates an attractive shaded error region rather than discrete bars.
Hi Yong Ho,
Thank you for your comment.
The linear mapping is just a option. You don't need to use that. But, the training requires the initial parameters. I think the linear mapping is one of candidates for initial parameters.
If you know better initial parameter setting, please let me know.
26 Feb 2014
4D/3D image visualization and evaluation GUI.