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

[Marcus Edel]

Maybe you can provide more information about the problem with the existing layers? I'm not sure I completely understand the problem.

I don't like the idea duplicating code, maybe we can workaround the problem or change the existing layer interface. I guess it wouldn't be a huge problem if we change the layers, so that they can be initialized with an activation function.

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/451#issuecomment-150193738
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151022/b9ec1aaf/attachment.html>