Machine learning(4):Linear regression
A Linear Model
This line has the equation y = c + mx where c is the intercept on the y axis and m is the gradient. Thus we need a method of determining c and m so that the equation is a good predictor of the value of y corresponding to a given value of x.
How to be a good prodictor?
There are six point beside the regression line, but we could calcluate the distance of each point from this line. If the value of distance is miniuted, it means the good regression line.
Make the value as small as possible(Minimising RMS Error )
HOW GOOD IS THE LINEAR MODEL?
The r means the great thing of this line. So, when the r is 1, it means it is the best fit.