Abstract | ||
---|---|---|
This paper presents two algorithms to aid the supervised learning of feedforward neural networks. Specifically, an initialization and a learning algorithm are presented. The proposed methods are based on the independent optimization of a subnetwork using linear least squares. An advantage of these methods is that the dimensionality of the effective search space for the non-linear algorithm is reduced, and therefore it decreases the number of training epochs which are required to find a good solution. The performance of the proposed methods is illustrated by simulated examples. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1007/3-540-44989-2_11 | ICANN |
Keywords | Field | DocType |
feedforward neural network,simulated example,good solution,effective search space,non-linear algorithm,linear least-squares,supervised learning,independent optimization,training epoch,neural network,search space | Least squares,Computer science,Artificial intelligence,Linear programming,Artificial neural network,Linear least squares,Feedforward neural network,Pattern recognition,Algorithm,Supervised learning,Curse of dimensionality,Initialization,Machine learning | Conference |
Volume | ISSN | ISBN |
2714 | 0302-9743 | 3-540-40408-2 |
Citations | PageRank | References |
7 | 0.68 | 10 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Oscar Fontenla-Romero | 1 | 337 | 39.49 |
Deniz Erdogmus | 2 | 1299 | 169.92 |
J. C. Principe | 3 | 658 | 46.92 |
Amparo Alonso-Betanzos | 4 | 885 | 76.98 |
Enrique Castillo | 5 | 555 | 59.86 |