Abstract | ||
---|---|---|
The paper presents a growing algorithm for the learning of a radial basis function (RBF) density estimation network. The algorithm resembles to the Adaptive Resonance Theory (ART) algorithms in that it recruits kernels when the current network can not account for the newly observed datum. The recruiting mechanism is based, however, on a model-complexity criterion rather than a vigilance parameter. The algorithm adjusts the network parameters as well as the number of hidden nodes so as to optimize network's performance as a parsimonious density estimator. Simulation results for a set of experiments show the good performance of the algorithm, in terms of both estimation accuracy and the number of deployed kernels, as compared to a vigilance parameter-based algorithm. |
Year | Venue | Keywords |
---|---|---|
1998 | ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3 | kernel density estimation, radial-basis function, growing algorithm |
Field | DocType | Citations |
Density estimation,Pattern recognition,Computer science,Artificial intelligence,Artificial neural network | Conference | 0 |
PageRank | References | Authors |
0.34 | 1 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mahdad Nouri Shirazi | 1 | 12 | 3.52 |
Hideki Noda | 2 | 227 | 31.14 |
Ikuo Yonemoto | 3 | 0 | 0.34 |
Hidefumi Sawai | 4 | 69 | 18.04 |