Or you can train multiple ones with a kind of evolutionary approach - e.g. you t... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		margorczynski on March 26, 2023 \| parent \| context \| favorite \| on: Robot Learns to See in 30 Minutes (2022) Or you can train multiple ones with a kind of evolutionary approach - e.g. you train 100 at the same time and after a day you take the one with the best results, overwrite the rest with it's weights/config/etc. and repeat until satisfied.

chiefalchemist on March 27, 2023 [–]

Right. But it's not the learning. It's the ability to scale what's learned.

Humans learns one by one by one effectively in silos.

Robots? There's no comparison.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact