Machine Learning Crash Course

Re:Machine Learning Crash Course by bluetwo on Thursday March 01, 2018 @05:03PM (#16496809)

I can't help but think in 3-5 years how quaint our tools of the day will seem.

[ Parent | on HN ]

Re:Machine Learning Crash Course by achompas on Thursday March 01, 2018 @06:12PM (#16497282)

I think about this constantly.

Not to sound like I walked uphill in both directions back in my day or something, but I remember building models in numpy without pandas. It was tedious -- and that's just a nice API wrapping ndarrays!

[ Parent | on HN ]

Re:Machine Learning Crash Course by bhrgunatha on Thursday March 01, 2018 @11:51PM (#16499136)

> Not to sound like I walked uphill in both directions back in my day

Local minima?

[ Parent | on HN ]

Re:Machine Learning Crash Course by YeGoblynQueenne on Friday March 02, 2018 @06:23AM (#16500627)

Most likely, gradient descent with momentum.

[ Parent | on HN ]

Re:Machine Learning Crash Course by farazbabar on Friday March 02, 2018 @08:33AM (#16501206)

Oh boy, that and perturbation.

[ Parent | on HN ]

Re:Machine Learning Crash Course by jimbokun on Thursday March 01, 2018 @11:49PM (#16499127)

I’m not so sure.

You can make an argument current tools haven’t really surpassed a Lisp Machine for developer productivity, or a SmallTalk environment.

[ Parent | on HN ]

Re:Machine Learning Crash Course by noobermin on Friday March 02, 2018 @03:20AM (#16499942)

Not really. I see things like leftpad and npm fails and CEOs mailing private keys they've stored from customers. I see the same lessons we have have to re-learn year after year.

[ Parent | on HN ]