Benjamin Lee

@SiminaB I just addressed your first point in the PR for #241. Specifically, I mentioned TF and PyTorch as well as Keras, AutoKeras, Turi Create, and TPOT. If there are...

It's doable in some cases but not really ideal. In my experience, I've always ended up having to use a cloud machine for training all but the simplest models. I've...

Definitely a good idea to speak affirmatively to what DL needs.

Thank you for adding it here and glad to see nothing else is blocking. I'll work on #237 once we do the content freeze since that is cosmetic.

I think that's a good idea. @chevrm do you want to PR it or should I?

@pstew and @SiminaB the data simulation paragraph just jumped out at me for feeling out of place both content-wise and stylistically. I'm tempted to cut it down to a sentence...

@pstew review requested for #269

I think we need to make it clearer that it's not only that you shouldn't share the model weights (white box attacks) but even allow people to submit their own...

I think you're right; it belongs in the "know your data" tip. It does inflate accuracy, but it's not due to memorization.

I've gone and removed the heritability part in #241 and am moving the part from tip 2 over now