News for hackers. Stuff that matters.

A comment on Bag of Tricks for Efficient Text Classification. Parent comment

Re:Bag of Tricks for Efficient Text Classification by rcpt on Saturday July 09, 2016 @10:05PM (#12064233)
I think bag of pixels would be more analogous to a bag of characters. A bag of words is more like a bag of SIFT features.
[ Parent | on HN ]
Re:Bag of Tricks for Efficient Text Classification by msandford on Sunday July 10, 2016 @11:51AM (#12065973)
Sure but n-gram feature extraction is what, five lines of code? It's a trivial transform compared to SIFT.

If you don't do SIFT manually prior to classification then your NN has to evolve something "similar" in order to work. Which is why it needs to be deep.

[ Parent | on HN ]