| Автор | M. Bouten |
| Автор | C. van den Broeck |
| Дата выпуска | 1994-04-01 |
| dc.description | We calculate the generalization error for the nearest-neighbour classifier based on a set of random examples generated by a teacher perceptron. Explicit results are given for dimensions N = 2, N = 3 and N → ∞. For a natural extension of the nearest-neighbour rule which includes the k-nearest-neighbour rule and the Hebbian perceptron as particular cases it is found that the Hebbian perceptron gives the smallest generalization error. |
| Формат | application.pdf |
| Издатель | Institute of Physics Publishing |
| Название | Nearest-Neighbour Classifier for the Perceptron |
| Тип | lett |
| DOI | 10.1209/0295-5075/26/1/012 |
| Electronic ISSN | 1286-4854 |
| Print ISSN | 0295-5075 |
| Журнал | EPL (Europhysics Letters) |
| Том | 26 |
| Первая страница | 69 |
| Последняя страница | 74 |
| Аффилиация | M. Bouten; Limburgs Universitair Centrum - B-3590 Diepenbeek, Belgium |
| Аффилиация | C. van den Broeck; Limburgs Universitair Centrum - B-3590 Diepenbeek, Belgium |
| Выпуск | 1 |
