Neural network objective functions for detection problems

Weber David ; Breitenbach Jaco (1997)

Conference Paper

We examine the effects of the choice of neural network objective (criterion) functions on the ability of the neural network to perform detection. The experiments are performed using a multilayer perceptron with the mean square error, classification figure of merit (CFM), maximally flat CFM and the modified perceptron error objective functions. We develop a thresholding scheme for the outputs of the neural network in order to obtain receiver operating characteristic (ROC) curves for the various objective functions. We perform preliminary tests on a breast cancer cell detection problem.

Please refer to this item in SUNScholar by using the following persistent URL: http://hdl.handle.net/10019.1/10445
This item appears in the following collections: