Comparative study of different types of wavelet functions in neural network

Mohammad Fazle Azeem; Ahmad Banakar; Vinod Kumar; IEEE

doi:10.1109/IJCNN.2006.246806

Back

Conference proceeding

Comparative study of different types of wavelet functions in neural network

Mohammad Fazle Azeem, Ahmad Banakar, Vinod Kumar and IEEE

2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, pp.1061-1066

IEEE International Joint Conference on Neural Networks (IJCNN)

01/01/2006

DOI: https://doi.org/10.1109/IJCNN.2006.246806

Abstract

Computer Science

Computer Science, Artificial Intelligence

Science & Technology

Technology

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.

Metrics

1 Record Views

Details

Title: Comparative study of different types of wavelet functions in neural network
Creators - without role: Mohammad Fazle Azeem - Aligarh Muslim University
Ahmad Banakar - Aligarh Muslim University
Vinod Kumar - Aligarh Muslim University
IEEE
Publication Details: 2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, pp.1061-1066
Series: IEEE International Joint Conference on Neural Networks (IJCNN)
Publisher: IEEE
Number of pages: 2
Identifiers: 9924056508331
Academic Unit: King Khalid University
Language: English
Resource Type: Conference proceeding