Function mse_loss 

pub fn mse_loss<B>(
    prediction: &Tensor<B>,
    target: &Tensor<B>,
) -> Result<Tensor<B>, Error>
where
    B: Backend,

Mean Squared Error loss: mean((prediction - target)²)

Both prediction and target must have the same shape. Returns a scalar tensor.

Example

let loss = mse_loss(&y_pred, &y_true)?;
let grads = loss.backward()?;