Mixture Density Networks (MDNs) are a well-established method for modelling the conditional probability density which is useful for complex multi-valued functions where regression methods (such as MLPs) fail. In this paper we extend earlier research of a regularisation method for a special case of MDNs to the general case using evidence based regularisation and we show how the Hessian of the MDN error function can be evaluated using R-propagation. The method is tested on two data sets and compared with early stopping.
|Title of host publication||Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000. IJCNN 2000|
|Place of Publication||United States|
|Publisher||IEEE Computer Society|
|Number of pages||6|
|Publication status||Published - 1 Aug 2000|
- Bayes methods, learning, artificial intelligence, neural nets, Bayesian training, MDN error function, mixture density networks, R-propagation, conditional probability density