| Автор | K Y M Wong |
| Автор | D Sherrington |
| Дата выпуска | 1990-02-21 |
| dc.description | The authors consider synaptic neural networks which minimise the output error of the stored patterns when the input patterns are ensembles of their noisy versions with overlap m<sub>t</sub> with the clean patterns. When m<sub>t</sub> is infinitesimally less than 1, the network automatically attains maximal stability, confirming the usefulness of training noises in enhancing memory associativity. When m<sub>t</sub> drops below 1, the field distribution has two bands for large m<sub>t</sub>, and one continuous band for small m<sub>t</sub>. Errorless retrieval is impossible for training noises of the order N<sup>0</sup>. With the increase in training noise, the retrieval overlap deteriorates, although memory associativity does increase for sufficiently low storage. |
| Формат | application.pdf |
| Издатель | Institute of Physics Publishing |
| Название | Training noise adaptation in attractor neural networks |
| Тип | lett |
| DOI | 10.1088/0305-4470/23/4/009 |
| Print ISSN | 0305-4470 |
| Журнал | Journal of Physics A: Mathematical and General |
| Том | 23 |
| Первая страница | L175 |
| Последняя страница | L182 |
| Аффилиация | K Y M Wong; Dept. of Phys., Imperial Coll., London, UK |
| Аффилиация | D Sherrington; Dept. of Phys., Imperial Coll., London, UK |
| Выпуск | 4 |
