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

stereomatchingkiss notifications at github.com
Mon Sep 21 02:13:03 EDT 2015


This commit intent to complete two things

1 : improve the speed of SparseAutoencoder
I cache the computation result in the data member, so the algorithm do not need to compute it two times.Since the member function is const, I declared the data member as mutable;Do anyone think that make the member function as non-const would be better?

2 : make the SparseAutoencoder more versatile
I add two template parameters as following

template<typename HiddenLayer, typename OutputLayer>
class SparseAutoencoderFunction;

This allow users use different layer from ann two compute the features
You can view, comment on, or merge this pull request online at:

  https://github.com/mlpack/mlpack/pull/451

-- Commit Summary --

  * improve speed of SparseAutoencoder and make it more flexible

-- File Changes --

    A src/mlpack/methods/ann/activation_functions/lazy_logistic_function.hpp (90)
    A src/mlpack/methods/ann/sparse_autoencoder_function.hpp (388)

-- Patch Links --

https://github.com/mlpack/mlpack/pull/451.patch
https://github.com/mlpack/mlpack/pull/451.diff

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/451
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20150920/e258947f/attachment.html>


More information about the mlpack-git mailing list