ZOLLNER, R and SCHMITZ, HJ and WUNSCH, F and KREY, U (1992) FAST GENERATING ALGORITHM FOR A GENERAL 3-LAYER PERCEPTRON. NEURAL NETWORKS, 5 (5). pp. 771-777. ISSN 0893-6080,
Full text not available from this repository.Abstract
A fast iterative algorithm is proposed for the construction and the learning of a neural net achieving a classification task, with an input layer, one intermediate layer, and an output layer The network is able to learn an arbitrary training set. The algorithm does not depend on a special learning scheme (e.g., the couplings can be determined by modified Hebbian prescriptions or by more complex learning procedures). During the process the intermediate units are constructed systematically by collecting the patterns into smaller subsets. For simplicity, we consider only the case of one output neuron, but actually this restriction is not necessary.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | NETWORKS; GENERAL PERCEPTRONS; INTERMEDIATE LAYER; FAST GENERATING ALGORITHM |
| Depositing User: | Dr. Gernot Deinzer |
| Last Modified: | 19 Oct 2022 08:44 |
| URI: | https://pred.uni-regensburg.de/id/eprint/54409 |
Actions (login required)
 |
View Item |
