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

> ML works well, when it is only trained on correct data.

Is that correct? I would think that its ‘interpolation’ and ‘extrapolation’ capabilities can easily make it produce incorrect statements.

As a simple example, train it on “π is a number”, “1 is a number”, “3/7 is a number”, “1.3457 is a number”, etc.

and

“1 is a rational number”, “3/7 is a rational number”, “1.3457 is a rational number”, etc.

and I give you a good chance that it will ‘think’ “π is a rational number”.



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

Search: