Using Neural Networks to Model Conditional Multivariate Densities
1996; The MIT Press; Volume: 8; Issue: 4 Linguagem: Inglês
10.1162/neco.1996.8.4.843
ISSN1530-888X
Autores Tópico(s)Fault Detection and Control Systems
ResumoNeural network outputs are interpreted as parameters of statistical distributions. This allows us to fit conditional distributions in which the parameters depend on the inputs to the network. We exploit this in modeling multivariate data, including the univariate case, in which there may be input-dependent (e.g., time-dependent) correlations between output components. This provides a novel way of modeling conditional correlation that extends existing techniques for determining input-dependent (local) error bars.
Referência(s)