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

[stereomatchingkiss]

After some experiments, not all of the layers of ann are suitable for SparseAutoencoder, it need to do some modification(ex : you cannot just call the dropout function, you need to call the activation function like sigmoid or RELU after calling Forward), I would like to open two new folders

1 : SparseAutoencoder/layers
2 : SparseAutoencoder/activation_functions
to collect the useable layers and activation functions, the implementation will based on the layers and activation functions of ann

Besides, I think the function "GetNewFeatures" of SparseAutoencoder should call the activation function of the hidden layer rather the Sigmoid.

I will remove LazyLogisticFunction and remove the check of LogisticFunction as zoq mentioned

Any suggestions?

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/451#issuecomment-149474303
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151020/4860ed89/attachment-0001.html>