The multilayer perceptron as an approximation to a Bayes optimal discriminant function

Authors:
D. W. Ruck;S. K. Rogers;M. Kabrisky;M. E. Oxley;B. W. Suter
Affiliations:
Sch. of Eng., US Air Force Inst. of Technol., Wright-Patterson AFB, OH;-;-;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
1990

Citing 0
Cited 10

Classifier ensembles: Select real-world applications

Information Fusion
Improving performance of neural classifiers via selective reduction of target levels

Neurocomputing
Bayesian decision theory on three-layer neural networks

Neurocomputing
Loss functions to combine learning and decision in multiclass problems

Neurocomputing
Classifier combination based on confidence transformation

Pattern Recognition
Breast cancer classification applying artificial metaplasticity algorithm

Neurocomputing
WBCD breast cancer database classification applying artificial metaplasticity neural network

Expert Systems with Applications: An International Journal
Neural network tomography: Network replication from output surface geometry

Neural Networks
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
Predicting students' final performance from participation in on-line discussion forums

Computers & Education

Quantified Score

Hi-index	0.00

Visualization

Abstract

The multilayer perceptron, when trained as a classifier using backpropagation, is shown to approximate the Bayes optimal discriminant function. The result is demonstrated for both the two-class problem and multiple classes. It is shown that the outputs of the multilayer perceptron approximate the a posteriori probability functions of the classes being trained. The proof applies to any number of layers and any type of unit activation function, linear or nonlinear