News for hackers. Stuff that matters.

A comment on Myths in Machine Learning Research.

Re:Myths in Machine Learning Research by edmack on Monday February 25, 2019 @07:56PM (#19251100)
Nice refreshing list :)

I didn't think "Attention > Convolution" was a prevalent myth, given how integral convolutions are to SOTA image classifiers and GANs (if anything, I believe attention is unde-utilised here and due to grow in usage a lot)

[ Parent | on HN ]
Re:Myths in Machine Learning Research by sdenton4 on Monday February 25, 2019 @10:00PM (#19251665)
Ugh... This list seems like a mishmash of actual bad practices and active areas of discussion labeled 'myths...' which seems pretty harmful to me.
[ Parent | on HN ]