Name
Abstract | ||
|---|---|---|
In this paper, we propose an approach for shaping the adaptive radial basis functions through potential Junctions for the purposes of classification. We propose a multilayer Potential Function Generators neural network (PFUGAW) with two fundamental components., potential function generators (PFGs) and potential function entities (PFEs) which create the decision rules by constructing multivariate potential functions and adjusting the weights as well as the parameters of the cumulative potential functions. The two proposed criteria evaluate the NN performance during the learning phase and force PFUGAW to enter the dynamic phase and perform structural changes before entering the next learning cycle. The implementation of the presented method with several data sets demonstrates its power in generating classification solutions for learning samples of various shapes. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/ICSMC.2005.1571241 | SMC |
Keywords | Field | DocType |
learning (artificial intelligence),multilayer perceptrons,radial basis function networks,adaptive radial basis functions,cumulative potential functions,decision rules,multilayer potential function generators neural network,multivariate potential functions,potential function entities,radial basis neural networks,Potential function generators,neural networks,radial basis functions | Decision rule,Data set,Radial basis function network,Radial basis function,Computer science,Activation function,Signal generator,Types of artificial neural networks,Artificial intelligence,Artificial neural network,Machine learning | Conference |
Volume | ISSN | Citations |
1 | 1062-922X | 0 |
PageRank | References | Authors |
0.34 | 5 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Iren Valova | 1 | 136 | 25.44 |
| George Georgiev | 2 | 5 | 4.48 |
| Natacha Gueorguieva | 3 | 63 | 12.46 |