“Deep Learning has outlived its usefulness as a buzz-phrase”

Re:“Deep Learning has outlived its usefulness as a buzz-phrase” by woodson on Friday January 05, 2018 @09:04PM (#16083420)

I’m in favor of getting rid of „neural“. That would help dispense with all the unhelpful discussions about how different DNNs work compared to the human brain.

[ Parent | on HN ]

Re:“Deep Learning has outlived its usefulness as a buzz-phrase” by jclos on Saturday January 06, 2018 @06:02AM (#16084749)

I agree. I've taken to calling them computational graphs in my lab, because that's what they are. There is nothing neural about a LSTM.

[ Parent | on HN ]