Liang, HL (reprint author), Chinese Acad Sci, Inst High Energy Phys, Ctr Comp, POB 9187, Beijing 100039, Peoples R China.
Cascade Correlation (CC) as a constructive algorithm for artificial neural networks stands out for solving hard classification problems. In this note we propose an extension of this technique that uses genetic algorithm for finding a good initialization point and yields improved results. The performance of our method is demonstrated on benchmark problems. (C) 1998 Published by Elsevier Science Inc. All rights reserved.