[mlpack-git] [mlpack] improve speed of SparseAutoencoder and make it more flexible (#451)

[stereomatchingkiss]

>If we pass the Weights and the RhoCap parameter we have to handle the pass of the parameter inside of the fnn class

Do you mean rather than

    SparseErrorFunction(hiddenLayer.Weights(), outputLayer.Weights(), hiddenLayer.RhoCap(), 
                        beta, lambda)

Pass whole network into it would be better?

    SparseErrorFunction(network, beta, lambda)

I have no problem with this one, if you think it is ok I would start to implement it.

>If you like, to provide some code, I'll be happy to merge the changes. But don't feel obligated.

Ok, would try to implement it if I got time

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/451#issuecomment-162486551
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151207/85580735/attachment.html>