Why machine learning struggles with causality

Re:Why machine learning struggles with causality by jonplackett on Friday April 02, 2021 @12:16PM (#26672779)

I saw a study a while back that kids only a few months old will preferentially go to a person who helped their mum open a jar rather than one who refused.

There’s a hell of a lot of observation happening in kids minds very early on.

No doubt it’s easier once you can pick up a baseball bat yourself, but I have no doubt a young kid would understand basic objects connected together without ever having used them.

[ Parent | on HN ]

Re:Why machine learning struggles with causality by mempko on Saturday April 03, 2021 @12:28AM (#26678443)

Exactly. People aren't born a blank slate. We have brain structures for understanding objects in the world and also language. A baby can automatically detect speech from other sounds. Evolution is a learning process it turns out.

[ Parent | on HN ]

Re:Why machine learning struggles with causality by watwut on Saturday April 03, 2021 @03:34AM (#26679019)

Few monts old kids cant go anywhere. 6 month old kids are starting to crawl and then they are unable to get where they want for some time.

And there is incredible amount of experimentation at that age. They dont learn things by observation alone for sure.

[ Parent | on HN ]