Data scaling for large dynamic range in neural networks

Question

The usual strategy in neural networks today is to use min-max scaling to scale the input feature vector from 0 to 1. I want to know if the same principle holds true if our inputs have a large dynamic range (for example, there may be some very large values and some very small values). Isn't it better to use logarithmic scaling in such cases?

SrJ · Answer

If it is a classification problem,  then you will use sigmoid or softmax to make the output value in (0,1) and all the value must sum to 1 as per the rule of probability.

Data scaling for large dynamic range in neural networks

One Answer

Add your own answers!

Ask a Question