Size reduction of a radial basis function network
| Autor: | B. Lemarie |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
Radial basis function network
Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Estimator Pattern recognition Backpropagation Reduction (complexity) Task (computing) Probabilistic neural network ComputingMethodologies_PATTERNRECOGNITION Feedforward neural network Radial basis function Artificial intelligence business |
| Zdroj: | Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan). |
| DOI: | 10.1109/ijcnn.1993.713924 |
| Popis: | We present a method of reducing the size of a radial basis function (RBF) network. The reduction is issued from the parallelism between RBF-networks and Parzen Windows estimator. We validate the method on a handwritten digit classification task. The resulting network is compared with the k-nearest neighbour statistical method. The results appear better for the network at a much lower computational cost. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|