Answers are grounded in this paper and cite their sources.
class probabilities. Interpretation of network outputs as Bayesian probabilities allows outputs from multiple networks to be combined for higher level decision making, simplifies creation of rejection thresholds, makes it possible to compensate for differences between pattern class probabilities in training and test data, allows outputs to be used to minimize alternative risk functions, and suggests alternative measures of network performance.
No takes yet. Share an insight, caveat, or question.
Richard et al. (1991) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: