2
$\begingroup$

Regression is often given as a simple example for supervised learning because you have a dependent variable and try to build a model with the independent variables.

Could you say that correlation is a simple example of unsupervised learning because you don't differentiate between dependent and independent variables and try to find a pattern in all variables simultaneously (like with clustering which is always given as the example of unsupervised learning)?

$\endgroup$
10
  • 4
    $\begingroup$ Can correlation be considered a type of learing at all? Correlation is a parameter of a bivariate distribution, just like mean or variance. Is mean a type of learning then, too? I don't know the answer, so this is an honest question. (Not that I would have an easy time with the regression model.) $\endgroup$ May 5, 2018 at 9:35
  • $\begingroup$ @RichardHardy: Another observation is that there are many similarities between linear regression and correlation - see also here: stats.stackexchange.com/questions/2125/… and here: stats.stackexchange.com/questions/108640/… $\endgroup$
    – vonjd
    May 5, 2018 at 10:03
  • $\begingroup$ @RichardHardy: See also my answer here: stats.stackexchange.com/a/344619/230 $\endgroup$
    – vonjd
    May 5, 2018 at 11:08
  • 1
    $\begingroup$ @RichardHardy: I don't want to get too philosophical but in the end learning in the ML sense is always nothing else but finding some (statistical) parameters of the data. $\endgroup$
    – vonjd
    May 5, 2018 at 11:38
  • 1
    $\begingroup$ I don't have one, sorry about that. Perhaps there are some in earlier threads. There must be. Perhaps here. $\endgroup$ May 5, 2018 at 20:01

1 Answer 1

1
$\begingroup$

Yes. I would say so. Typical other example for unsupervised learning is density estimation and clustering. To me, there is on a meta level no difference between estimating a density, estimating labels to learn clusters and estimating a correlation.

$\endgroup$
1
  • 2
    $\begingroup$ However, I don't like the term "learning". I agree that these are "unsupervised" as in they are not given an explicit value to predict. But is the use of the tent "learning" really justified? Correlation is just a number. $\endgroup$ May 6, 2018 at 17:07

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.