| Автор | D R C Dominguez |
| Автор | W K Theumann |
| Дата выпуска | 1996-02-21 |
| dc.description | The generalization ability of an extremely dilute feedback neural network with multi-state neurons is studied by means of a deterministic noiseless parallel dynamics. The overlap with any one of a macroscopic number of binary, full activity, concepts is determined when the network is trained with examples of variable activity according to a Hebbian learning algorithm that favours stable symmetric mixture states. Explicit results about the phase diagram and the generalization error are obtained for a network with three-state neurons which remain inactive below a threshold . It is shown that the generalization ability can be considerably enhanced either by training the network with low-activity examples or by means of a moderate increase in . |
| Формат | application.pdf |
| Издатель | Institute of Physics Publishing |
| Название | Generalization in a multi-state neural network |
| Тип | paper |
| DOI | 10.1088/0305-4470/29/4/006 |
| Print ISSN | 0305-4470 |
| Журнал | Journal of Physics A: Mathematical and General |
| Том | 29 |
| Первая страница | 749 |
| Последняя страница | 761 |
| Выпуск | 4 |
