[mlpack-git] [mlpack] FFN serialization (#516)

[Marcus Edel]

Joseph is right, we don't have to save the input, output and gradient parameter. We don't need the parameter for optimizing an already trained model nor for testing.

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/516#issuecomment-183068885
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160211/f5eb289e/attachment-0001.html>