|
| << vorige | volgende >> |
Tijdschrift beschrijving
Alle jaargangen van het bijbehorende tijdschrift
Alle afleveringen van het bijbehorende jaargang
Alle artikelen van de bijbehorende aflevering
Details van artikel 2 van 13 gevonden artikelen
| Titel: |
Associative ability of higher order correlation models for sequential patterns |
| Auteur: |
Miyajima, Hiromi Shigei, Noritaka |
| Verschenen in: |
International journal of knowledge-based intelligent engineering systems |
| Paginering: | Jaargang 10 (2006) nr. 6 pagina's 403-416 |
| Jaar: |
2006-12-12 |
| Inhoud: |
This paper describes some results on transition properties and the absolute capacities of higher order correlation and differential correlation associative memories. First, it is shown that the absolute capacities are (1-$\bar{s}$)2/2(1-$\bar{s}$2)1-k log N and {2(1-$\bar{s}$2)k-1}2/2k+2(1-$\bar{s}$2)1-k log N for correlation and differential correlation models, respectively, where N is the number of neurons, $\bar{s}$ is the rate of correlation for patterns and k is the dimension. The results show that the absolute capacities approach to 0 rapidly as N increases in both models and they decrease rapidly in the correlation model and slowly in the differential correlation model as $\bar{s}$ increases. Further, it is clarified that the correlation model is superior in storage capacities and inferior in robustness than the differential correlation one. |
| Uitgever: |
IOS Press |
| Bronbestand: |
Elektronische Wetenschappelijke Tijdschriften |
Details van artikel 2 van 13 gevonden artikelen
| << vorige | volgende >> |