Training Wavelet Networks for Nonlinear Dynamic Input-Output Modeling

Yacine Oussar (1) , Isabelle Rivals (1) , Léon Personnaz (1) , Gerard Dreyfus (1)

1 Laboratoire d'Electronique

In the framework of nonlinear process modeling, we propose training algorithms for feedback wavelet networks used as nonlinear dynamic models. An original initialization procedure is presented, that takes the locality of the wavelet functions into account. Results obtained for the modeling of several processes are presented; a comparison with networks of neurons with sigmoidal functions is performed.

Mots clés: Training; Wavelet networks; Nonlinear dynamic modeling; Neural networks; Feedback networks; Recurrent networks

Domaines: Machine Learning [stat.ML]; Réseau de neurones [cs.NE]

Yacine Oussar, Isabelle Rivals, Léon Personnaz, Gerard Dreyfus. Training Wavelet Networks for Nonlinear Dynamic Input-Output Modeling. Neurocomputing, 1998, 20 (1-3), pp.173-188. ⟨hal-00797616⟩