Performance and generalization of the classification figure of merit criterion function

A criterion function-the classification figure of merit (CFM)-for training neural networks, introduced by J.B. Hampshire and A.H. Waibel (IEEE Trans. Neural Networks, vol. 1, pp. 216-218, June (1990)), is studied. It is shown that this criterion function has some highly desirable properties. CFM has optimal training-set performance, which is related (but not equivalent) to its monotonicity. However, there is no reason to expect generalization with this criterion function to be substantially better than that of the standard criterion functions. It is nonetheless preferable to use this criterion function because its ability to find classifiers which classify the training set well will also lead to improved test-set performance after training with a suitably detailed training set