Maybe it could be worth to extend the normalizer with
some options, and a first, simple but effective option
could be a logarithmic transformation.
Here is why (extraction from
"... By taking logarithms, you are effectively
measuring errors in terms of ratios rather than
differences, since a difference between two logs
corresponds to the ratio of the original values. This
has approximately the same effect as looking at
percentage differences, abs(target-output)/target or
abs(target-output)/output, rather than simple
Log in to post a comment.