BNNSLossFunctionMeanSquareError
Mean square error (MSE) computation between input logits and one-hot encoded labels.
Declaration
var BNNSLossFunctionMeanSquareError: BNNSLossFunction { get }Discussion
BNNSLossFunctionMeanSquareError performs mean square error (MSE) computation between input logits and one hot encoded labels.
You can scale the loss with either a scalar value or weight matrix, and reduce the loss according to a reduction function.