On the design principles of the functional link nets
- 4 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
A necessary and sufficient condition for the nonexistence of a local stationary point for functional link nets is derived. The condition reveals the dependency of training errors on the rank of training samples and functional links and provides a guideline for selection of the functional links as well as training samples. An analytical solution is characterized, showing that the training task in the functional link nets can be reduced to solving a set of linear equations. A learning algorithm based on the recursive-least squares estimation method is proposed. Numerical examples are presented to substantiate the theoretical argumentsKeywords
This publication has 5 references indexed in Scilit:
- Robust control of nonlinear systems using pattern recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Back propagation fails to separate where perceptrons succeedIEEE Transactions on Circuits and Systems, 1989
- On training of artificial neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Characteristics of the functional link net: a higher order delta rule netPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Polynomial Theory of Complex SystemsIEEE Transactions on Systems, Man, and Cybernetics, 1971