A new constrained learning algorithm for function approximation by encoding a priori information into feedforward neural networks

Authors:
Fei Han;De-Shuang Huang
Affiliations:
Jiangsu Univ., School of Comp. Sci. and Telecommunication Engineering, 212013, Zhenjiang, Jiangsu, China and Chinese Academy of Sciences, Intelligent Computing Lab, Hefei Institute of Intelligent ...;Chinese Academy of Sciences, Intelligent Computing Lab, Hefei Institute of Intelligent Machines, P.O.Box 1130, 230031, Hefei, Anhui, China
Venue:
Neural Computing and Applications
Year:
2008

Citing 0
Cited 2

A constrained approximation algorithm by encoding second-order derivative information into feedforward neural networks

ICIC'09 Proceedings of the Intelligent computing 5th international conference on Emerging intelligent computing technology and applications
Gene selection and PSO-BP classifier encoding a prior information

ICSI'10 Proceedings of the First international conference on Advances in Swarm Intelligence - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a new learning algorithm which encodes a priori information into feedforward neural networks is proposed for function approximation problem. The new algorithm considers two kinds of constraints, which are architectural constraints and connection weight constraints, from a priori information of function approximation problem. On one hand, the activation functions of the hidden neurons are specific polynomial functions. On the other hand, the connection weight constraints are obtained from the first-order derivative of the approximated function. The new learning algorithm has been shown by theoretical justifications and experimental results to have better generalization performance and faster convergent rate than other algorithms.