In this paper, a hierarchical Bayesian learning scheme for autoregressive neural network models is shown which overcomes the problem of identifying the separate linear and nonlinear parts modelled by the network. We show how the identification can be carried out by defining suitable priors on the parameter space which help the learning algorithms to avoid undesired parameter configurations. Some applications to synthetic and real world experimental data are shown to validate the proposed methodology.
A hierarchical Bayesian framework for nonlinearities identification in gravitational wave detector outputs
ACERNESE, Fausto;BARONE, Fabrizio;TAGLIAFERRI, Roberto
2005-01-01
Abstract
In this paper, a hierarchical Bayesian learning scheme for autoregressive neural network models is shown which overcomes the problem of identifying the separate linear and nonlinear parts modelled by the network. We show how the identification can be carried out by defining suitable priors on the parameter space which help the learning algorithms to avoid undesired parameter configurations. Some applications to synthetic and real world experimental data are shown to validate the proposed methodology.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.