Considering that it’s squaring the error and the error is between zero and 1 MSE would be pointless in predicting values in that range correct?

If it’s indeed useless for that range, would using RMSE allow us to use this loss function at 0-1 range to benefit from its outlier sensitivity during training?

Edit: the expected output is a range between 0-1 i.e a regression problem not a classification problem.

In a NN regression problem, considering that MSE is squaring the error and the error is between 0 and 1 would it be pointless to use MSE as our loss function during model training?

For example:

MSE = (y_pred - y_true) ^ 2 

@ Expected model output range [0, 1]:
MSE = (0.1 - 0.01) ^ 2 = 0.0081

// Significantly larger error is less pronounced in the MSE output
MSE = (0.1 - 0.0001) ^ 2 = 0.00998001


@ Expected model output range [10, 20]:
MSE = (10 - 12) ^ 2 = 4

// Significantly larger error is more pronounced in the MSE output
MSE = (10 - 20) ^ 2 = 100

If it’s indeed useless for that range, would using RMSE allow us to use this loss function at 0-1 range to benefit from its outlier sensitivity during training or is there another loss that would mimic the effect of MSE for values between 0 and 1?

Considering that it’s squaring the error and the error is between zero and 1 MSE would be pointless in predicting values in that range correct?

If it’s indeed useless for that range, would using RMSE allow us to use this loss function at 0-1 range to benefit from its outlier sensitivity during training?

Considering that it’s squaring the error and the error is between zero and 1 MSE would be pointless in predicting values in that range correct?

If it’s indeed useless for that range, would using RMSE allow us to use this loss function at 0-1 range to benefit from its outlier sensitivity during training?

Edit: the expected output is a range between 0-1 i.e a regression problem not a classification problem.

Considering that it’s squaring the error and the error is between zero and 1 MSE would be pointless in predicting values in that range correct?

Considering that it’s squaring the error and the error is between zero and 1 MSE would be pointless in predicting values in that range correct?

If it’s indeed useless for that range, would using RMSE allow us to use this loss function at 0-1 range to benefit from its outlier sensitivity during training?