mean square error

Terms from Artificial Intelligence: humans at the heart of algorithms

The glossary is being gradually proof checked, but currently has many typos and misspellings.

The mean square error is a form of accuracy measure. It is the arithmetic mean of the squares of the errors. That is, if xi is a sequence of 'true' values (perhaps from training data) and pi is a corresponding sequence of estmates/predictions, then:
        mean square error   =   &Sigma (xi − pi)2 ) / N
Sometimes the sqoare root of this used, called (predictably!) the root mean square error (RMS).