Abstract | ||
---|---|---|
In this article we define globally convergent decomposition algorithms for supervised training of generalized radial basis function neural networks. First, we consider training algorithms based on the two-block decomposition of the network parameters into the vector of weights and the vector of centers. Then we define a decomposition algorithm in which the selection of the center locations is split into sequential minimizations with respect to each center, and we give a suitable criterion for choosing the centers that must be updated at each step. We prove the global convergence of the proposed algorithms and report the computational results obtained for a set of test problems. |
Year | DOI | Venue |
---|---|---|
2001 | 10.1162/08997660152469396 | Neural Computation |
Keywords | DocType | Volume |
neural network,two-block decomposition,training rbf neural networks,computational result,center location,generalized radial basis function,global convergence,convergent decomposition techniques,supervised training,network parameter,decomposition algorithm,convergent decomposition algorithm | Journal | 13 |
Issue | ISSN | Citations |
8 | 0899-7667 | 7 |
PageRank | References | Authors |
0.54 | 4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Buzzi, C | 1 | 7 | 0.54 |
L Grippo | 2 | 273 | 24.32 |
M. Sciandrone | 3 | 335 | 29.01 |