Associative switch for combining multiple classifiers

Explores the possibility of using a neural-net approach to the task of combining multiple classifiers. A combination principle is proposed, and a novel combination technique, called an associative switch, is developed for solving the problem. The switch is controlled by a neural net trained by the backpropagation technique with a modified energy criterion. When an unlabeled pattern is the input to each individual classifier, it also goes to the neural net for associatively calling out a code which controls the switch to decide whether the result of each classifier could pass through as a final result. This associative switch is applied to a problem of combining multiple classifiers for recognizing totally unconstrained handwritten numerals.<<ETX>>