This finds the mean of the squared errors:
MSE = mean(errors.^2)
Each element is squared separately, and then the mean of the resulting vector is found.
Domanda
I don't know whether this is possible or not but let me explain my question
Imagine that I have the below array
errors=[e1,e2,e3];
Now what I want to calculate is below
MSE=1/(array_lenght)*[e1^2+e2^2+e3^2];
I can make this with a loop but I wonder if there is any quick way.
Soluzione
This finds the mean of the squared errors:
MSE = mean(errors.^2)
Each element is squared separately, and then the mean of the resulting vector is found.
Altri suggerimenti
sum(errors.^2) / numel(errors)
Raising powers and adding can be done together instead of sequentially:
MSE = (errors*errors') / numel(errors)