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

[stereomatchingkiss]

About the part of prediction, if I could access underlying network, it would be easier

    using ActivateFunction = typename HiddenLayer::ActivateFunction;

    arma::mat const encodeInput = w1 * input+ arma::repmat(b1, 1, input.n_cols);
    ActivateFunction::fn(encodeInput , features);

As you can see, to extract the features from the input, I do not need to forward the whole layers, I would need to access underlying network of the FFN, could I add a public api to access the network?

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/451#issuecomment-164171021
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151212/2c32423f/attachment.html>