1
$\begingroup$

How do machine learning models (including neural networks) respond to the presence of a nonlinear attribute among predictors in a training set?

$\endgroup$
2
  • 3
    $\begingroup$ You need to clarify what you mean by "nonlinear attribute". Are you saying there is a nonlinear relationship observed between the attribute and the response? We can guess that that's what you mean, but as it is currently written the question doesn't really make sense. $\endgroup$
    – klumbard
    Jan 22, 2020 at 18:24
  • $\begingroup$ Yes, one of the attributes has a non-linear relationship to the response. $\endgroup$
    – Anatoliy
    Jan 23, 2020 at 7:46

1 Answer 1

1
$\begingroup$

It depends what you mean by machine learning. Smoothing splines are used to model non-linear effects and the properties of the regression function (e.g., the smoothness of the regression function) are often determined through cross validation. I would consider that falling into the same category as what many people mean when they refer to machine learning.

$\endgroup$
2
  • $\begingroup$ Within my domain (task area) the term "machine learning", I assume, means the ability to predict the value of response (dependent variable) based on a training set with several attributes (predictors). $\endgroup$
    – Anatoliy
    Jan 23, 2020 at 7:54
  • $\begingroup$ Then yes smoothing splines would fall into that category and appears responsive to your query about non-linear covariate effects. $\endgroup$ Jan 23, 2020 at 12:56

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.