Recognition Networks for Approximate Inference in BN2O Networks (2001)
by
Quaid Morris
| Venue: | In Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence |
| Citations: | 3 - 1 self |
BibTeX
@INPROCEEDINGS{Morris01recognitionnetworks,
author = {Quaid Morris},
title = {Recognition Networks for Approximate Inference in BN2O Networks},
booktitle = {In Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence},
year = {2001}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
A recognition network is a multilayer perception (MLP) trained to predict posterior marginals given observed evidence in a particular Bayesian network. The input to the MLP is a vector of the states of the evidential nodes. The activity of an output unit is interpreted as a prediction of the posterior marginal of the corresponding variable. The MLP is trained using samples generated from the corresponding Bayesian network.
