Multi-category Bayesian Decision by Neural Networks

Authors:
Yoshifusa Ito;Cidambi Srinivasan;Hiroyuki Izumi
Affiliations:
School of Medicine, Aichi Medical University, Nagakute-cho, Japan 480-1195;Department of Statistics, University of Kentucky, Lexington, USA 40506;Department of Policy Science, Aichi-Gakuin University, Nisshin-shi, Japan 470-0195
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 6
Cited 2

Multilayer neural networks and Bayes decision theory

Neural Networks
Review:

Neural Computation
Simultaneous approximations of polynomials and derivatives and their applications to neural networks

Neural Computation
Bayesian decision theory on three-layer neural networks

Neurocomputing
Bayesian learning of neural networks adapted to changes of prior probabilities

ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Discriminant analysis by a neural network with mahalanobis distance

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II

A new algorithm for learning mahalanobis discriminant functions by a neural network

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part II
Simultaneous learning of several bayesian and mahalanobis discriminant functions by a neural network with memory nodes

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part V

Quantified Score

Hi-index	0.02

Visualization

Abstract

For neural networks, learning from dichotomous random samples is difficult. An example is learning of a Bayesian discriminant function. However, one-hidden-layer neural networks with fewer inner parameters can learn from such signals better than ordinary ones. We show that such neural networks can be used for approximating multi-category Bayesian discriminant functions when the state-conditional probability distributions are two dimensional normal distributions. Results of a simple simulation are shown as examples.