This Is AuburnElectronic Theses and Dissertations

Show simple item record

Training Arbitrarily Connected Neural Networks with Second Order Algorithms


Metadata FieldValueLanguage
dc.contributor.advisorWilamowski, Bogdan
dc.contributor.advisorRoppel, Thaddeusen_US
dc.contributor.advisorHung, Johnen_US
dc.contributor.authorCotton, Nicholasen_US
dc.date.accessioned2008-09-09T22:36:17Z
dc.date.available2008-09-09T22:36:17Z
dc.date.issued2008-08-15en_US
dc.identifier.urihttp://hdl.handle.net/10415/1187
dc.description.abstractNeural networks have been an active area of research and application for many years. Today they are gaining popularity with the growing processing power of modern computers. With neural networks gaining popularity comes a demand for a simple and reliable method of training all types of networks which is the focus of this paper. Neural Network Trainer is a training package that allows the user to create a simple netlist style network architecture in a text file and quickly begin training. Several algorithms are implemented including Error Back Propagation as well modified versions of the Levenberg-Marquardt algorithm. The software is demonstrated with results verifying the implemented algorithms as well as the trained neural networks.en_US
dc.language.isoen_USen_US
dc.subjectElectrical and Computer Engineeringen_US
dc.titleTraining Arbitrarily Connected Neural Networks with Second Order Algorithmsen_US
dc.typeThesisen_US
dc.embargo.lengthNO_RESTRICTIONen_US
dc.embargo.statusNOT_EMBARGOEDen_US

Files in this item

Show simple item record