3

i'm wondering why in a Wavelet Neural Network, there is no Inverse Transform that recompose the signal?

How come only the wavelet coefficients are enough to find the wanted signal?

Wouldn't it be better to have the IWT?

Jeff

Felipe Oriani
  • 37,948
  • 19
  • 131
  • 194
IonOne
  • 385
  • 4
  • 15

1 Answers1

0

The use of wavelets in neural network is just for features extractions. And from wavelets decompositions you can restore the original signal. Another point about your question is. Are you using the WNN for regression or classification? In case of classification there's no need for IWT. In case of regression i don't know how to fit WNN.

sugestion: Wavelet Neural Networks

Community
  • 1
  • 1
David Clifte
  • 359
  • 4
  • 12