News for hackers. Stuff that matters.
Re:Why “Gradient” Descent? by nodemaker on Friday January 03, 2020 @02:24PM (#21949364)
Yeah thats what the gradient literally is defined as = Rate of change. Not trying to be snarky but for me this means not taking the time to learn the basics before jumping into far far advanced concepts. Sadly this seems to be a pattern in a lot of machine learning curriculum today.
Re:Why “Gradient” Descent? by fxtentacle on Friday January 03, 2020 @03:39PM (#21950088)
When private schools offer a 1-year course to become a "Machine Learning Consultant" with no prior mathematics or programming knowledge required, you know that something has to be off ...
Re:Why “Gradient” Descent? by TrackerFF on Friday January 03, 2020 @05:43PM (#21951108)
I mean, a quality program will include both numerical analysis and optimization methods classes in their program, both which will (hopefully) go through things like gradient descent in rigour.

And long before that students will hopefully have a solid fundamental knowledge in what rate of change means - not just as in banging out derivatives on paper.