DocumentCode :
2768160
Title :
Comparative Study of Different Types of Wavelet Functions in Neural Network
Author :
Azeem, M.F. ; Banakar, Ahmad ; Kumar, Vinod
Author_Institution :
Aligarh Muslim Univ., Aligarh
fYear :
0
fDate :
0-0 0
Firstpage :
1061
Lastpage :
1066
Abstract :
Based on the wavelet transform theory, the new notion of the wavelet network is proposed as an alternative to feed forward neural networks for approximating arbitrary nonlinear functions. Boubez employed ortho-normal wavelets; Yamakawa, Uchino and Samatsu proposed two types of new neuron models and named Wavelet Synapse (WS) neuron and Wavelet Activation (WA) function neuron. These models are obtained by modifying the Mc Culloch and Pitts neuron model with non-orthogonal wavelet bases. Comparative study of different type of Wavelet functions is carried out in this paper by applying above two neuron models.
Keywords :
feedforward neural nets; function approximation; nonlinear functions; wavelet transforms; feed forward neural network; nonlinear function approximation; nonorthogonal wavelet function; wavelet activation function neuron model; wavelet synapse neuron model; wavelet transform theory; Continuous wavelet transforms; Educational institutions; Intelligent networks; Neural networks; Neurons; Performance analysis; Signal analysis; Signal resolution; Wavelet analysis; Wavelet transforms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
Type :
conf
DOI :
10.1109/IJCNN.2006.246806
Filename :
1716217
Link To Document :
بازگشت