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

stereomatchingkiss notifications at github.com
Wed Sep 23 00:17:16 EDT 2015

>can I get a little more information on how you calculated that?
Of course, the file sparse_autoencoder_function already provide the example, I hope this is a correct way to measure the performance

>This file looks like it's heavily based on the code in mlpack/methods/sparse_autoencoder/sparse_autoencoder_function.hpp
Yes, I put it in ann mainly because this class break the old api and SparseAutoEncoder looks looks like part of the family member of neural network(I am not an expert of neural network, please correct me if I am wrong), for backward compatibility I do not change the original version. 

> But maybe it would be a better idea to make this class work with the Trainer class in src/mlpack/methods/ann/
I do not know how to make it work yet, but if this could work, it should be able to provide unified interface. I think I would wait for the comments of zoq's.

Reply to this email directly or view it on GitHub:
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20150922/92c020b9/attachment.html>

More information about the mlpack-git mailing list