powered by
The root of the Mean Squared Error between the exact value and the predicted one.
RMSE(Y, Ypred)
a real which represents the root of the mean squared error between the target response \(Y\)
and the fitted one \(\hat{Y}\): $$\code{RMSE} = \sqrt{\frac{1}{n} \sum_{i=1}^{n} \left( Y \left( x_{i}\right)-\hat{Y} \left( x_{i}\right)\right)^2}.$$
a real vector with the values of the output
a real vector with the predicted values
D. Dupuy
other validation criteria as MAE or RMA
MAE
RMA
X <- seq(-1,1,0.1) Y <- 3*X + rnorm(length(X),0,0.5) Ypred <- 3*X print(RMSE(Y,Ypred))
Run the code above in your browser using DataLab