Using Neural Networks to Model Conditional Multivariate Densities

1 May 1996

journal article
Published by MIT Press in Neural Computation

Vol. 8 (4) , 843-854
https://doi.org/10.1162/neco.1996.8.4.843

Abstract

Neural 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.

Keywords

This publication has 4 references indexed in Scilit:

Bayesian Regularization and Pruning Using a Laplace Prior
Neural Computation, 1995
Curvature-driven smoothing: a learning algorithm for feedforward networks
IEEE Transactions on Neural Networks, 1993
Simplifying Neural Networks by Soft Weight-Sharing
Neural Computation, 1992
Adaptive Mixtures of Local Experts
Neural Computation, 1991