Dorocicz, John Tadeusz2024-08-132024-08-1319971997https://hdl.handle.net/1828/17637This thesis will outline the basis for some types of artificial neural networks. In particular a special type of recurrent neural network that has been proven to be asymptotically stable will be studied. The theory required to train such a neural network will be presented. A number of heuristics designed to improve the training of the asymptotically stable recur­rent neural network and the results of these heuristics on a variety of data sets will be pre­sented. An application for the asymptotically stable recurrent neural network involving the monitoring of cable television trunk amplifiers will also be described.134 pagesAvailable to the World Wide WebThesis