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

[Marcus Edel]

I prefer the first version. In fact, I've implemented the negative log likelihood for another model, which also requires the error value, so now there isn't just one function that requires an interface modification.

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/451#issuecomment-163740664
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151210/9a0cbec8/attachment.html>