Sum-of-squares loss

Formula: E = (1/2) sum_i sum_j (y-hat_ij - y_ij)^2 (eq. 10.5), the loss whose partial derivatives with respect to the weights drive backpropagation.

Usage

Msm249(y_hat, y)

Arguments

y_hat

Predicted output matrix.

y

Observed output matrix.

Value

List with estimate, sse, method.

References

Montesinos Lopez, Montesinos Lopez & Crossa (2022), Multivariate Statistical Machine Learning Methods for Genomic Prediction, Springer, eq. (10.5) p.409. DOI 10.1007/978-3-030-89010-0.

Examples

V <- c(1, 2, 3, 4, 5, 6, 7, 8)
Msm249(V, V)
#> $estimate
#> [1] 0
#> 
#> $sse
#> [1] 0
#> 
#> $method
#> [1] "SSE loss (MVSML 2022 eq. 10.5)"
#>