Artificial (or biological) Neural Networks must be able to form by learning internal memory of the environment to determine decisions and subsequent actions to stimuli. By assuming that environment is essentially stochastic it follows that the mathematical framework for learning information from environment is the theory of stochastic processes approximation. The aim of this paper is to show that classes of neural networks capable of approximating stochastic processes exist.
Artificial neural networks as approximators of stochastic processes / Belli, M. R.; Conti, Massimo; Crippa, Paolo; Orcioni, Simone; Turchetti, Claudio. - 2:(1998), pp. 627-632. (Intervento presentato al convegno 8th International Conference on Artificial Neural Networks (ICANN98) tenutosi a Skovde, Svezia nel 2 - 4 Settembre 1998) [10.1007/978-1-4471-1599-1_95].
Artificial neural networks as approximators of stochastic processes
CONTI, MASSIMO;CRIPPA, Paolo;ORCIONI, Simone;TURCHETTI, Claudio
1998-01-01
Abstract
Artificial (or biological) Neural Networks must be able to form by learning internal memory of the environment to determine decisions and subsequent actions to stimuli. By assuming that environment is essentially stochastic it follows that the mathematical framework for learning information from environment is the theory of stochastic processes approximation. The aim of this paper is to show that classes of neural networks capable of approximating stochastic processes exist.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
