Wouldn't you "just" need to train a classifier on top to select the best fitting... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

ratsimihah on Jan 12, 2018 | parent | context | favorite | on: One model to learn them all

Wouldn't you "just" need to train a classifier on top to select the best fitting model? Or use ensemble learning? I dunno. My point is that it wouldn't be much more generalized even without that input.

nicolashahn on Jan 12, 2018 [–]

Yeah, that would just be one step out of the however dozens/hundreds/thousands more to go before AGI.

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