On 11/28/2011 05:23 PM, Timmy Wilson wrote: > Thanks Guys! > >> This is neither a Deep Belief Network nor a stack >> of RBMs, just a regular feed forward neural network >> that has a particularly well chosen set of initial weights. > Agreed. This is what i'm imagining. > > Assuming good results, i'm sure i'll want to move to a GPU implementation. > > Initially though, i'm just experimenting/learning, and not really > concerned w/ speed. > > Specifically i'm comparing neural nets w/ other dimension reduction > methods (NMF, LDA, the new dictionary learning implementation, ect..) > > It seems like the only piece i'm missing is the backprop piece. > > Andy, do you think it would be easy to pull that piece out of CUV > stack, and use it in the proposed toy implementation? > I think it should be pretty straightforward, replacing cp.prod() with np.dot() and similar. The implementation has lots of features, so I am not sure how easy it is to understand. You can definitely have a look.
If you already have a working RBM implementation, it might be easier to code the back propagation step yourself. Maybe you should rather look at some backpropagation code and the paper the others suggested. Implementing backpropagation should be fairly straight-forward. ------------------------------------------------------------------------------ All the data continuously generated in your IT infrastructure contains a definitive record of customers, application performance, security threats, fraudulent activity, and more. Splunk takes this data and makes sense of it. IT sense. And common sense. http://p.sf.net/sfu/splunk-novd2d _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
