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

[Marcus Edel]

Ah I missed the beta and lambda parameter, I guess in this case we should go with your suggested interface. I thought we could extract every information from the network, which would result in a single parameter we have to pass to the performance function.

>Ok, would try to implement it if I got time

Sounds, great, I do the same if I have the time.

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/451#issuecomment-162689355
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151207/b259be09/attachment.html>