Question

Could we use validation set & LOOCV for any supervised learning approach?
Or only for KNN?

Answer 1

Hope you find this helpful and give a'like'.

Solution :

Yes , validation set and LOOCV ( Leave one out cross validation) can be used for supervised learning approach . This is basically because the training set is used to generate multiple splits of the Train and Validation sets . Cross validation avoids over-fitting for which it becomes a desirable procedure. The K- fold Cross Validation is most useful.

KNN algorithm can be used for various purposes, mainly unsupervised learning like clustering and supervised learning like classification and regression.
Note that , KNN is just an algorithm to find nearest data points based on a given distance metric.
Cross validation can be used for supervised learning not unsupervised. To apply cross validation we need to understand the context of our purpose and not just base our judgement on the fact that it is KNN or not.

Thank you.