Si veda l'allegato.
In this paper we propose a Monte Carlo-based learning algorithm which is able to associate to the estimator of each weight of a given multi-layer perceptron a probability distribution converging in distribution to the standardized normal one. Moreover, the learning algorithm performs a global search in the space of the weights.
Multi-layer perceptron learning via Monte Carlo approach: A proposal
CORAZZA, Marco
2004-01-01
Abstract
In this paper we propose a Monte Carlo-based learning algorithm which is able to associate to the estimator of each weight of a given multi-layer perceptron a probability distribution converging in distribution to the standardized normal one. Moreover, the learning algorithm performs a global search in the space of the weights.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
2004-Corazza-Multi-layer_perceptron_learning_via_Monte_Carlo_approach_A_proposal-RENDICONTI.pdf
accesso aperto
Descrizione: Articolo nella versione dell'editore.
Tipologia:
Versione dell'editore
Licenza:
Accesso libero (no vincoli)
Dimensione
4.12 MB
Formato
Adobe PDF
|
4.12 MB | Adobe PDF | Visualizza/Apri |
I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.