SupervisedLearning
In supervisedlearning, we are given a data set and already know what our correct outputshould look like, having the idea that there is a relationship between theinput and the output.
Supervisedlearning problems are categorized into "regression" and"classification" problems. In a regression problem, we are trying topredict results within a continuous output, meaning that we are trying to mapinput variables to some continuous function. In a classification problem, weare instead trying to predict results in a discrete output. In other words, weare trying to map input variables into discrete categories.
Example 1:
Given data aboutthe size of houses on the real estate market, try to predict their price. Priceas a function of size is a continuous output, so this is a regression problem.
We could turnthis example into a classification problem by instead making our output aboutwhether the house "sells for more or less than the asking price."Here we are classifying the houses based on price into two discrete categories.
Example 2:
(a) Regression -Given a picture of a person, we have to predict their age on the basis of thegiven picture
(b)Classification - Given a patient with a tumor, we have to predict whether thetumor is malignant or benign.
