Hacker News new | ask | show | jobs
by schoen 3242 days ago
You might have seen it called "regression" (also "interpolation" and "extrapolation"), but not everyone has necessarily been exposed to this.
2 comments

Related, I used to jokingly explain mean-square-error approximation like this: there is this geometrical theorem, that you can drive a line through any three points on a plane, as long as the line is thick enough. So mean-square-error approximation is basically minimizing the thickness of that line :).
New favorite alternative term for deep learning: "nonlinear interpolation"