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 the recursive-least-squares estimation method is proposed. Numerical examples are presented to substantiate the theoretical arguments.
Original language | English |
---|---|
Title of host publication | Proceedings of the IEEE International Conference on Systems Engineering 1990 |
Publisher | IEEE |
Pages | 613-616 |
ISBN (Print) | 0-7803-0173-0 |
DOIs | |
Publication status | Published - Aug 1990 |
Externally published | Yes |
Event | IEEE International Conference on Systems Engineering 1990 - Pittsburgh, United States Duration: 9 Aug 1990 → 11 Aug 1990 |
Conference
Conference | IEEE International Conference on Systems Engineering 1990 |
---|---|
Country/Territory | United States |
City | Pittsburgh |
Period | 9/08/90 → 11/08/90 |