Learns from data labeled with the right answer(label Y)
Regression: Predict a number among infinitely many possible numbers/outputs
Linear Regression: Fitting a straight line to your data
Classification: Predict categories from among a limited set of categories.
There are only a few possible outputs/categories/classes.
Categories could be non_numeric or numeric.
The learning algorithm has to decide how to fit a boundary line through this data.
The boundary line is found by the learning algorithm.
Logistic Regression: Fitting a curve that looks like S-shape curve to the dataset