Neural network objective functions for detection problems
dc.contributor.author | Weber David | |
dc.contributor.author | Breitenbach Jaco | |
dc.date.accessioned | 2011-05-15T15:57:31Z | |
dc.date.available | 2011-05-15T15:57:31Z | |
dc.date.issued | 1997 | |
dc.description.abstract | 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. | |
dc.description.version | Conference Paper | |
dc.identifier.citation | Proceedings of the South African Symposium on Communications and Signal Processing, COMSIG | |
dc.identifier.uri | http://hdl.handle.net/10019.1/10445 | |
dc.subject | Algorithms | |
dc.subject | Error detection | |
dc.subject | Probability | |
dc.subject | Classification figure of merit (CFM) | |
dc.subject | Receiver operating characteristics (ROC) curves | |
dc.subject | Neural networks | |
dc.title | Neural network objective functions for detection problems | |
dc.type | Conference Paper |