How to modify RMSE loss function to adopt for integer valued predictions, using a Neural Network?

by Ambareesh   Last Updated August 14, 2019 03:19 AM

Context: Prediction of dependent variables like Age, Siblings, Children, etc (which are not categorical, but bounded, and integer-valued) from a dataset using Neural Network. I'm experimenting with a simple network, and plan to train it using Gradient Descent for starters.

While RMSE is a natural choice for minimization, the predictions currently are float values. I could probably round the predictions (or ceil/floor them) and calculate the loss (again using RMSE), but is that a correct approach?

Related Questions

Updated October 02, 2017 05:19 AM

Updated January 24, 2019 18:19 PM

Updated March 17, 2016 08:08 AM

Updated March 08, 2018 08:19 AM

Updated April 07, 2017 13:19 PM