Data scaling for large dynamic range in neural networks

Question

Data scaling for large dynamic range in neural networks

Rishabh Jain

2022年4月7日 18:06

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?

Topic preprocessing feature-scaling neural-network

Category Data Science

SrJ · Accepted Answer · 2020年6月21日 10:42

1

SrJ answered at 2020年6月21日 10:42

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

About