Ryan Curtin

Sure, that is one idea. I think that probably the ERT won't be useful until we have some kind of random forest class to ensemble them, but I am working...

Here is another potential idea for a numeric split that I came across today: http://web.cs.iastate.edu/~honavar/elomaa-multisplit.pdf

There have been no updates on this, so you are welcome to implement something.

I definitely agree that we should rework our documentation and README to point to our support for embedded devices and cross-compilation. I think maybe the easiest way to go, for...

Yeah, that could be a nice addition!

I'd love to transition our tutorials to Sphinx (and our documentation too!) but it would be a good bit of work. #1877 discussed it; maybe it is actually getting close...

Note that this is dependent on #1494 being merged, since it won't work with the old style of SGD impostor calculation which only computed impostors for small batches at a...

@manish7294: sorry, I forgot to tag you in this! Take a look and let me know what you think when you have a chance.

@darthgera123 all of them are still there. There are many other stale/closed PRs that you could resurrect and finish also. I suggest searching through the closed PRs. Some digging will...

Sorry for the slow response on this one. I appreciate the contribution! But, is this any different than if the user simply made one `LinearRegression` model for each column of...