| Автор | I Pérez Castillo |
| Автор | B Wemmenhove |
| Автор | J P L Hatchett |
| Автор | A C C Coolen |
| Автор | N S Skantzos |
| Автор | T Nikoletopoulos |
| Дата выпуска | 2004-09-17 |
| dc.description | We study the influence of network topology on retrieval properties of recurrent neural networks, using replica techniques for dilute systems. The theory is presented for a network with an arbitrary degree distribution p(k) and applied to power-law distributions p(k) ∼ k<sup>−γ</sup>, i.e. to neural networks on scale-free graphs. A bifurcation analysis identifies phase boundaries between the paramagnetic phase and either a retrieval phase or a spin-glass phase. Using a population dynamics algorithm, the retrieval overlap and spin-glass order parameters may be calculated throughout the phase diagram. It is shown that there is an enhancement of the retrieval properties compared with a Poissonian random graph. We compare our findings with simulations. |
| Формат | application.pdf |
| Издатель | Institute of Physics Publishing |
| Копирайт | 2004 IOP Publishing Ltd |
| Название | Analytic solution of attractor neural networks on scale-free graphs |
| Тип | paper |
| DOI | 10.1088/0305-4470/37/37/002 |
| Print ISSN | 0305-4470 |
| Журнал | Journal of Physics A: Mathematical and General |
| Том | 37 |
| Первая страница | 8789 |
| Последняя страница | 8799 |
| Выпуск | 37 |
