A Sparse Infrastructure of Wavelet Network for Nonparametric Regression

In this paper, we propose a novel 4-layer infrastructure of wavelet network. It differs from the commonly used 3-layer wavelet networks in adaptive selection of wavelet neurons based on the input information. As a result, it not only alleviates widespread structural redundancy, but can also control the scale of problem solution to a certain extent. Based on this architecture, we build a new type of wavelet network for function learning. The experimental results demonstrate that our model is remarkably superior to two well-established 3-layer wavelet networks in terms of both speed and accuracy. Another comparison to Huang’s real-time neural network shows that, at similar speed, our model achieves improvement in generalization performance. abstract environment.

Authors and Affiliations

1. Center for Brain-Computer Interface and Brain Information Processing, South China University of Technology, Guangzhou, 510640, China

   Jun Zhang, Zhenghui Gu & Yuanqing Li

2. Information Engineering College, Guangdong University of Technology, Guangzhou, 510006, China

   Jun Zhang

3. Information Engineering College, Xiangtan University, Xiangtan, 411105, China

   Xieping Gao

Editors and Affiliations

1. Department of Computer Science and Engineering, Shanghai Jiao Tong University, 800 Dongchuan Road, 200240, Shanghai, China

   Liqing Zhang

2. Department of Computer Science and Engineering, Shanghai Jiao Tong University, 800, Dongchuan Road, 200240, Shanghai, China

   Bao-Liang Lu

3. Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Clear Water bay, Kowloon, Hong Kong, China

   James Kwok

Reprints and permissions

© 2010 Springer-Verlag Berlin Heidelberg

Policies and ethics