Neural networks and contagion
We analyze local as well as global interaction and contagion in population games, using the formalism of neural networks. In contrast to much of the literature, a state encodes not only the frequency of play, but also the spatial pattern of play. Stochastic best response dynamics with logistic noise...
Kaydedildi:
| Yayımlandı: | URI:https://journals.openedition.org/rei, |
|---|---|
| Asıl Yazarlar: | , , |
| Materyal Türü: | Article ou chapitre numérique |
| Dil: | Français |
| Baskı/Yayın Bilgisi: |
Revue d’économie industrielle
2007
|
| Konular: | |
| Online Erişim: | Accès Université d'Orléans et IFPM Accès Université d'Orléans et IFPM |
| Özet: | We analyze local as well as global interaction and contagion in population games, using the formalism of neural networks. In contrast to much of the literature, a state encodes not only the frequency of play, but also the spatial pattern of play. Stochastic best response dynamics with logistic noise gives rise to a log-linear or logit response model. The stationary distribution is of the Gibbs-Boltzmann type. The long-run equilibria are the maxima of a potential function. |
|---|