Paul Stewart

icon indicating a website link https://scholar.google.com/citations?user=xz4fP7cAAAAJ&hl=en

icon company Huntsman Cancer Institute icon location Salt Lake City, Utah icon location Associate Professor in the Department of Nutrition and Integrative Physiology; Investigator at Huntsman Cancer Institute (University of Utah)

Results 7 comments of Paul Stewart

Overall discussion for Tip 4

Agreed. It still feels out of place, even after it was moved (from tip 1?) and further tweaked (e.g. #234). Not sure about where it fits best but open to...

Overall discussion for Tip 4

@Benjamin-Lee I agree. Go for it.

Overall discussion for Tip 4

@Benjamin-Lee Thanks! Approved!

Perform sanity checks and follow good coding practices

@Benjamin-Lee Congrats! I think this and the paper linked by @agitter would be great to cite here.

Abstract as much as possible

Is it worth mentioning/discussing that the reader should do some sort of cost-benefit analysis of the setup required for learning some new system/toolkit vs. just hacking it together to get...

Make sure your problem is a good fit for deep learning.

Can this be combined with #3 ?

Use training/tuning/testing dataset terminology

I'm a fan of training/validating/testing myself, but I would be happy with whatever doesn't confuse readers. I think we should come to a consensus for consistency and then just mention...