Tweeted By @rasbt

"Statistical significance in deep learning papers?" (https://t.co/RB39xlkjrh) -- why is this not a thing in practice? My thoughts: (a) test sets are usually large enough; (b) reviewers trad. didn't ask for it (c) people don't like pitfalls (independence violations). Others?

— Sebastian Raschka (@rasbt) September 17, 2020