- Tytuł:
- On the Thermodynamics of the Hopfield Neural Network with External Field
- Autorzy:
-
Ulaczyk, J.
Kosiński, R. A.
Zagórski, A. - Powiązania:
- https://bibliotekanauki.pl/articles/2036992.pdf
- Data publikacji:
- 2003-11
- Wydawca:
- Polska Akademia Nauk. Instytut Fizyki PAN
- Tematy:
- 75.10.Hk
- Opis:
- In the paper thermodynamic properties of an artificial neural network are analyzed in a way analogous to spin glasses theory. Synaptic connections are calculated numerically according to the Hebb rule and their distribution is obtained for different characteristics of stored patterns. The phase diagrams and magnetization are established in dependence on the temperature of the network and the external field (threshold). It was showed that changing control parameters typical of artificial neural network (i.e. number of stored patterns and pattern bias level) one obtains the results similar to the Sherrington-Kirkpatrick model of spin glass.
- Źródło:
-
Acta Physica Polonica A; 2003, 104, 5; 479-486
0587-4246
1898-794X - Pojawia się w:
- Acta Physica Polonica A
- Dostawca treści:
- Biblioteka Nauki
Artykuł