1
$\begingroup$

In ML, I learned that we have a model and a learning algorithm. The learning algorithm is used to train the model with training data, does that sound correct?

If the model is trained using linear regression, then is it called a "linear model"?

In the same way, what are the models called which are trained using KNN, Naive Bayes, and SVM?

$\endgroup$
5
  • $\begingroup$ My last two questions are different so I need a better answer. $\endgroup$
    – Segnite
    Feb 24 '19 at 14:30
  • $\begingroup$ if that doesn't help then I'd also suggest reading Introduction to Statistical learning as the classifers you've mentioned are covered there $\endgroup$
    – vigos
    Feb 25 '19 at 14:02
  • $\begingroup$ What are the models called which are trained using KNN, Naive Bayes, and SVM? Are they called just classifiers? $\endgroup$
    – Segnite
    Feb 27 '19 at 7:03
  • $\begingroup$ The answers are there, at least implicitly. What people call something is largely cultural (opinion, convention, etc.). Most people will probably call something, say, 'a knn model' or 'a knn classifier', etc. There isn't much else to this. I'll add some additional links that may be helpful for you. $\endgroup$ Feb 27 '19 at 15:37
  • $\begingroup$ The model is not called a linear model because it is trained in a certain way but because its structural form is that of a linear equation. $\endgroup$
    – Digio
    Feb 27 '19 at 21:27