[mlpack-git] [mlpack] [Proposal]Enhance the class SparseAutoencoder and SoftmaxRegression (#454)

[stereomatchingkiss]

As one of the user of mlpack, I would like to have following features

1 : allow users to get the trained parameters of SparseAutoencoder and SoftmaxRegression 

According to UFLDL, if you want to finetune the stacked autoencoder, you will need the trained parameters of SparseAutoencoder and SoftmaxRegression, so I suggest add two functions to get and set the trained parameters of SparseAutoencoder and SoftmaxRegression 

ex : 
arma::mat parameters() const;
void parameters(arma::mat const &parameters);

2 : provide a default constructor for class SparseAutoencoder and SoftmaxRegression
This allow users to train the SparseAutoencoder or SoftmaxRegression later on, so the users do not need to wrap them in smart pointer just to delay the initialization time.

3 : This one is related to suggestion 2, provide a train function for SparseAutoencoder and SoftmaxRegression, this way the users can train the data whenever they like

ex : 
//for SoftMaxRegression
void train(arma::mat const &input, arma::vec const &label, size_t numOfLabels);

//for SparseAutoencoder
void train(arma::mat const &input, size_t hiddenSize);

The programs should be able to detect the inputSize from the input(input.n_cols), so the users do not need to set it

Exactly, these requirements almost finished on my computer, if you agree with the suggestions, I will send a pull request.Thank you very much

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/issues/454
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20150925/ed114d1b/attachment.html>