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

Ryan Curtin notifications at github.com
Tue Sep 22 22:38:43 EDT 2015


> +#include <mlpack/methods/ann/layer/base_layer.hpp>
> +
> +#include <boost/test/unit_test.hpp>
> +#include "old_boost_test_definitions.hpp"
> +
> +using namespace mlpack;
> +using namespace arma;
> +
> +using FSigmoidLayer = ann::SigmoidLayer<ann::LazyLogisticFunction>;
> +
> +//sparse autoencoder function
> +using SAEF = ann::SparseAutoencoderFunction<FSigmoidLayer, FSigmoidLayer>;
> +//sparse autoencoder function greedy
> +using SAEFG = ann::SparseAutoencoderFunction<FSigmoidLayer, FSigmoidLayer, std::true_type>;
> +
> +BOOST_AUTO_TEST_SUITE(SparseAutoencoderTest2);

Just a note -- when this is merged, we can remove the old `sparse_autoencoder_test.cpp` and revert this to `SparseAutoencoderTest` instead of `SparseAutoencoderTest2`.

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/451/files#r40166501
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20150922/b7e631fb/attachment.html>


More information about the mlpack-git mailing list