Name
Abstract | ||
|---|---|---|
The problem of training a radial basis function (RBF) neural network for distinguishing two disjoint sets in R(n) is considered. The network parameters can be determined by minimizing an error function that measures the degree of success in the recognition of a given number of training patterns. In this paper, taking into account the specific feature of classification problems, where the goal is to obtain that the network outputs take values above or below a fixed threshold, we propose an approach alternative to the classical one that makes use of the least-squares error function. In particular, the problem is formulated in terms of a system of nonlinear inequalities, and a suitable error function, which depends only on the violated inequalities, is defined. Then, a training algorithm based on this formulation is presented. Finally, the results obtained by applying the algorithm to two test problems are compared with those derived by adopting the commonly used least-squares error function. The results show the effectiveness of the proposed approach in RBF network training for pattern recognition, mainly in terms of computational time saving. |
Year | DOI | Venue |
|---|---|---|
2001 | 10.1109/72.950152 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
neural network,efficient training,pattern recognition,training algorithm,training pattern,rbf network training,least-squares error function,rbf neural network,error function,suitable error function,network parameter,network output,radial basis function,testing,error correction,learning artificial intelligence,computer networks,convergence,radial basis function network,network topology,neural networks | Error function,Radial basis function network,Radial basis function,Disjoint sets,Pattern recognition,Activation function,Computer science,Hierarchical RBF,Time delay neural network,Artificial intelligence,Artificial neural network,Machine learning | Journal |
Volume | Issue | ISSN |
12 | 5 | 1045-9227 |
Citations | PageRank | References |
12 | 0.72 | 6 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| F. Lampariello | 1 | 26 | 1.33 |
| M. Sciandrone | 2 | 335 | 29.01 |