Mean Squared Error
A loss function that measures prediction error by squaring the difference between predicted and actual values, heavily penalizing large errors.
Mean squared error (MSE) is a regression loss function that computes the average of squared differences between predictions and targets. The squaring operation makes MSE highly sensitive to outliers: an error of 10 counts as 100 times worse than an error of 1, not just 10 times. This property is desirable when large errors are genuinely catastrophic, but problematic when outliers represent noise rather than signal.
Also known as
MSE, squared error loss, L2 loss