Kohonen SOM Maps: Normalizing the input with unknown range
- by S.N
According to "Introduction to Neural Networks with Java By Jeff Heaton", the input to the Kohonen neural network must be the values between -1 and 1.
It is possible to normalize inputs where the range is known beforehand:
For instance RGB (125, 125, 125) where the range is know as values 0 and 255:
1. Divide by 255: (125/255) = 0.49 (0.49,0.49,0.49)
2. Multiply by two and subtract one: ((0.49*2)-1)=-0.02 (-0.02,-0.02,-0.02)
The question is how can we normalize the input where the range is unknown like our height or weight.
Also, some other papers mention that the input must be normalized to the values between 0 and 1. Which is the proper way, "-1 and 1" or "0 and 1"?