2

I have two questions:

  1. Do I have to apply Feature Scaling over ALL features in Neural Network(and Deep Learning too)?
  2. How can I scale categorical features in a dataset for neural network(if needed)?
Timbus Calin
  • 13,809
  • 5
  • 41
  • 59
Andrei
  • 73
  • 1
  • 13

1 Answers1

0

Its depends, what are you are trying to you could:

  1. Use one hot encoding, to create numeric values.

  2. For numerical features you could divide in each value into the average value for example, ant then you will will get values between [0,1], which make make it , good to feed a neural network.

Timbus Calin
  • 13,809
  • 5
  • 41
  • 59
Jonathan Lorence
  • 83
  • 1
  • 9
  • I try to predict some continous values depending on gender,annual income,age and i think the gender column is an important feature,isn't it? – Andrei Nov 05 '20 at 08:36