An integrity constraint for database systems containing embedded neural networks
Iain Millns, Barry Eaglestone · 2002
Neural networks are used in some database systems to classify objects, but like traditional statistical classifiers they often misclassify. For some applications, it is necessary to bound the proportion of misclassified objects. This is clearly an integrity problem. We describe a new integrity constraint for database systems with embedded neural networks, with which Database Administrator can enforce a bound on the proportion of misclassifications in a class. The approach is based upon mapping probabilities generated by a probablistic neural network to the likely percentage of misclassifications.