Share Email Print
cover

Proceedings Paper

Comparison of neuron selection algorithms of wavelet-based neural network
Author(s): Xiaodan Mei; Sheng-He Sun
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Wavelet networks have increasingly received considerable attention in various fields such as signal processing, pattern recognition, robotics and automatic control. Recently people are interested in employing wavelet functions as activation functions and have obtained some satisfying results in approximating and localizing signals. However, the function estimation will become more and more complex with the growth of the input dimension. The hidden neurons contribute to minimize the approximation error, so it is important to study suitable algorithms for neuron selection. It is obvious that exhaustive search procedure is not satisfying when the number of neurons is large. The study in this paper focus on what type of selection algorithm has faster convergence speed and less error for signal approximation. Therefore, the Genetic algorithm and the Tabu Search algorithm are studied and compared by some experiments. This paper first presents the structure of the wavelet-based neural network, then introduces these two selection algorithms and discusses their properties and learning processes, and analyzes the experiments and results. We used two wavelet functions to test these two algorithms. The experiments show that the Tabu Search selection algorithm's performance is better than the Genetic selection algorithm, TSA has faster convergence rate than GA under the same stopping criterion.

Paper Details

Date Published: 20 September 2001
PDF: 6 pages
Proc. SPIE 4555, Neural Network and Distributed Processing, (20 September 2001); doi: 10.1117/12.441684
Show Author Affiliations
Xiaodan Mei, Harbin Institute of Technology (China)
Sheng-He Sun, Harbin Institute of Technology (China)


Published in SPIE Proceedings Vol. 4555:
Neural Network and Distributed Processing

© SPIE. Terms of Use
Back to Top