Neural Network Classifiers Estimate Bayesian a posteriori Probabilities

@article{Richard1991NeuralNC,
  title={Neural Network Classifiers Estimate Bayesian a posteriori Probabilities},
  author={Michael D. Richard and Richard Lippmann},
  journal={Neural Computation},
  year={1991},
  volume={3},
  pages={461-483}
}
Many neural network classifiers provide outputs which estimate Bayesian a posteriori probabilities. When the estimation is accurate, network outputs can be treated as probabilities and sum to one. Simple proofs show that Bayesian probabilities are estimated when desired network outputs are 2 of M (one output unity, all others zero) and a squarederror or cross-entropy cost function is used. Results of Monte Carlo simulations performed using multilayer perceptron (MLP) networks trained with… CONTINUE READING
Highly Influential
This paper has highly influenced 23 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 517 extracted citations

Connectionist-based Dempster-Shafer evidential reasoning for data fusion

IEEE Transactions on Neural Networks • 2004
View 7 Excerpts
Highly Influenced

Automatic classification of land cover on Smith Island, VA, using HyMAP imagery

IEEE Trans. Geoscience and Remote Sensing • 2002
View 17 Excerpts
Highly Influenced

A Neural Network for Tornado Diagnosis: Managing Local Minima

Neural Computing & Applications • 2000
View 4 Excerpts
Highly Influenced

Neural networks for classification: a survey

IEEE Trans. Systems, Man, and Cybernetics, Part C • 2000
View 7 Excerpts
Highly Influenced

References

Publications referenced by this paper.
Showing 1-10 of 29 references

A comparative study of the practical characteristics of neural network and conventional pattern classifiers

P.
Tech. Rep. 894, MIT Lincoln Laboratory, Lexington, MA, March. Ng, K., and Lippmann, R. P. 1991b. A comparative study of the practical characteristics of neural network and conventional pattern classifiers. In • 1991

A note on least-squares learning procedures and clas

P A.
1991

A probabilistic approach to the understanding and training

D. Richard, H. Richard P. Lippmann Gish
1990

A probabilistic approach to the understanding and training of neural network classifiers

H. Richard P. Lippmann Gish
Proceedings of l € E € Conference on Acoustics Speech and Signal Processing • 1990

Competing experts: A n experimental investigation of associative mixture models

J.S.
Tech. Rep. CRG-TR-90-5, University of Toronto, September. Ruck, D. W., Rogers, S. K., Kabrisky, M., Oxley, M. E., and Suter, B. W. 1990. The multilayer perceptron as an approximation to a Bayes optimal discriminant function. • 1990

Similar Papers

Loading similar papers…