Hacker Read

inverse_pi | karma 232 | avg karma 2.97 · 2018-08-27 23:00:37+00:00

Explaining why this doesn't work is a great ML interview question.

alexsb92 | karma 353 | avg karma 2.25 · 2018-08-27 23:25:29+00:00

As someone not involved in ML, why doesn't it work?

perfmode | karma 2592 | avg karma 2.27 · 2018-08-28 00:28:33

reducing error on the training set doesn’t always generalize to an unseen test set

mcny | karma 3145 | avg karma 2.14 · 2018-08-28 02:41:04

Yup, I didn't learn much from my image analysis class but the professor made sure that over fitting and under fitting concepts were firmly lodged in our heads.

8note | karma 4988 | avg karma 1.12 · 2018-08-28 00:31:23+00:00

I don't want to subject my drivers to dangerous conditions to train my cars to handle them

david-gpu | karma 3356 | avg karma 3.7 · 2018-08-28 00:00:35

Well, there are companies out there (like drive.ai IIRC) training such models end-to-end, so it is not entirely out of the question.