[mlpack-git] [mlpack] [Proposal]Add a function to visualize the results of sparse_autoencoder (#452)

[stereomatchingkiss]

> So if your autoencoder has 40 hidden units, then that's 40 different maximal inputs that you want.

 You are correct and this should be easy to code. But in the actual cases, I think the users(like) would more interesting on visualize the whole images rather than visualize a single maximal input. I think one api "MaximalInput(maximalInput)" should be enough for this case

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/issues/452#issuecomment-150705588
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151023/2e24a318/attachment.html>