On the structure of strict sense Bayesian cost functions and its applications

IEEE Transactions on Neural Networks

Volumn 12, Issue 3, 2001, Pages 445-455

  Cid Sueiro, Jesús ^a,b   Figueiras Vidal, Aníbal R ^a,b  

^a IEEE   (Spain)

^b UNIVERSIDAD CARLOS III DE MADRID   (Spain)

Author keywords

Cost function; Entropy; Neural networks; Posterior probability estimation

Indexed keywords

BAYESIAN COST FUNCTION; ENTROPY MINIMIZATION;

ALGORITHMS; DECISION THEORY; ESTIMATION; LEARNING SYSTEMS; PROBABILITY;

NEURAL NETWORKS;

EID: 0035330125     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.925549     Document Type: Article

References (26)

1. Cost functions to estimate a posteriori probabilities in multiclass problems
2. The multilayer perceptron as an approximation to a Bayes optimal discriminant function
3. Neural network classifiers estimate Bayesian a posteriori probabilities
4. Neural network classification: A Bayesian interpretation
5. A new error criterion for posterior probability estimation with neural nets
6. Backpropagation and stochastic gradient descent method
7. Equivalence proofs for multi-layer perceptron classifiers and the Bayesian discriminant function
8. On loss functions which minimize to conditional expected values and posterior probabilities
9. Non-mean square error criteria for the training of learning machines
10. Hierarchical mixture of experts and the EM algorithm
11. Neural architectures for parametric estimation of a posteriori probabilities by constrained conditional density functions
12. Learning from incomplete data
13. The relative value of labeled and unlabeled samples in pattern recognition with an unknown mixing parameter
14. Classification accuracy improvement of neural network classifiers by using unlabeled data
15. Partially supervised classification using weighted unsupervised clustering
16. The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon
17. A mixture of experts classifier with learning based on both labeled and unlabeled data
18. Growing Gaussian mixtures network for classification applications
19. A method of generating objective functions for probability estimation