[mlpack-git] [mlpack] Create a function to visualize the features learned by sparse autoencoder (#465)
notifications at github.com
Tue Oct 27 09:34:32 EDT 2015
I've spent a bit of time thinking about it; you're right that unit tests are very hard to come up with for this case. Maybe a very simple one: if we train an autoencoder with a single hidden unit on the same input over and over again, then wouldn't the input that maximally activates that single hidden unit be the same input? That's a very simple test, but I don't know if we'll manage to have any very complex tests here...
Reply to this email directly or view it on GitHub:
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the mlpack-git