Why error measures are sub-optimal for training neural network pattern classifiers
- 2 January 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 220-227
- https://doi.org/10.1109/ijcnn.1992.227338
Abstract
Pattern classifiers that are trained in a supervisedfashion (e.g., multi-layer perceptrons, radial basis functions, etc.)are typically trained with an error measure objective function such as mean-squared error (MSE) or cross-entropy(CE). These classifiers can in theory yield (optimal) Bayesian discrimination, but in practice they often fail to doso. We explain why this happens. In so doing, we identify a number of characteristics that the optimal objectivefunction for training classifiers...Keywords
This publication has 5 references indexed in Scilit:
- Neural Network Classifiers Estimate Bayesian a posteriori ProbabilitiesNeural Computation, 1991
- Performance and generalization of the classification figure of merit criterion functionIEEE Transactions on Neural Networks, 1991
- A novel objective function for improved phoneme recognition using time-delay neural networksIEEE Transactions on Neural Networks, 1990
- A comparison between criterion functions for linear classifiers, with an application to neural netsIEEE Transactions on Systems, Man, and Cybernetics, 1989
- Parallel Distributed ProcessingPublished by MIT Press ,1987