[mlpack-git] [mlpack] implement command line programs of softmaxRegression (#466)

stereomatchingkiss notifications at github.com
Mon Nov 9 23:44:01 EST 2015


>Nah, you shouldn't have to do anything at all. You can use the SoftmaxRegression class with the L-BFGS optimizer like this:

I tried it as you said, but it cannot work, it do need to implement those three functions, unless you are not using SoftmaxRegressionFunction but SoftmaxErrorFunction to do the optimization. Do you mean I should use SoftmaxErrorFunction to optimize SoftmaxRegression rahter than using SoftmaxRegressionFunction if I plan to adopt SGD?

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/466#issuecomment-155285929
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151109/1cdd6a7c/attachment.html>


More information about the mlpack-git mailing list