| Автор | Michal Rosen-Zvi |
| Автор | Ido Kanter |
| Автор | Wolfgang Kinzel |
| Дата выпуска | 2002-11-29 |
| dc.description | The mutual learning process between two parity feed-forward networks with discrete and continuous weights is studied analytically, and we find that the number of steps required to achieve full synchronization between the two networks in the case of discrete weights is finite. The synchronization process is shown to be non-self-averaging and the analytical solution is based on random auxiliary variables. The learning time of an attacker that is trying to imitate one of the networks is examined analytically and is found to be much longer than the synchronization time. Analytical results are found to be in agreement with simulations. |
| Формат | application.pdf |
| Издатель | Institute of Physics Publishing |
| Название | Cryptography based on neural networks—analytical results |
| Тип | lett |
| DOI | 10.1088/0305-4470/35/47/104 |
| Print ISSN | 0305-4470 |
| Журнал | Journal of Physics A: Mathematical and General |
| Том | 35 |
| Первая страница | L707 |
| Последняя страница | L713 |
| Выпуск | 47 |
