Name
Abstract | ||
|---|---|---|
xIn pattern classification problems using a RBFNN classifier, the selection of the number of clusters and their corresponding centers influences the network's ability to generalize unseen data. In this paper, we evaluate different RBFNN architectures by a quantitative measure - RBFNN sensitivity measure, which is defined as the absolute expectation plus standard deviation of network output perturbations with respect to input perturbations. Numerical comparisons of a number of different RBFNN architectures are given using two of UCI datasets. The experiments show that the sensitivity measure would be correlated to the testing error for the unseen samples and simpler classification problem may have smaller sensitivity measure. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/ICSMC.2004.1400917 | 2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7 |
Keywords | Field | DocType |
radial basis function neural network (RBFNN), stochastic sensitivity measure, model evaluation, number of centers (RBF neurons), neural network performance assessment | Radial basis function network,Pattern recognition,Computer science,Stochastic process,Artificial intelligence,Classifier (linguistics),Standard deviation,Machine learning | Conference |
ISSN | Citations | PageRank |
1062-922X | 3 | 0.56 |
References | Authors | |
10 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wing W. Y. Ng | 1 | 528 | 56.12 |
| Daniel S. Yeung | 2 | 1126 | 92.97 |
| Ian Cloete | 3 | 132 | 16.61 |