# Why should I normalize also the output data?

I'm new to data science and Neural Networks in general. Looking around many people say it is better to normalize the data between doing anything with the NN. I understand how normalizing the input data can be useful.

However I really don't see how normalizing the output data can help.

I've also tried both cases with a easy dataset, and I achieved the same results. The only difference is that in some weird problems, it is really hard to then re-convert the output back.

Can you give me some intuition on why we should also normalize the output?

Or maybe why it is indifferent?

• Do you mean normalizing as in making zero mean and unit standard deviation or by scaling between 0 and 1 (or -1 and 1)? – MaximilianP Oct 31 '17 at 9:59
• between 0 and 1 – Euler_Salter Oct 31 '17 at 10:14
• Came here since I had the same question. I also didn't see the point. @tomar__'s answer is very helpful and it also explains why your case may not need the normalization. If each of your target variables is in the same range already, you probably don't have to normalize them to 0..1. – Cerno Feb 24 at 18:06

That paper gives a nice answer, where i quoted from. Search for Should I standardize the target variables (column vectors)? in that page.