Show simple item record

A Delay Damage Model Selection Algorithm for NARX Neural Networks

dc.contributor.authorLin, Tsungnanen_US
dc.contributor.authorGiles, C. Leeen_US
dc.contributor.authorHorne, Bill G.en_US
dc.contributor.authorKung, Sun-Yangen_US
dc.date.accessioned2004-05-31T22:42:05Z
dc.date.available2004-05-31T22:42:05Z
dc.date.created1996-12en_US
dc.date.issued1998-10-15en_US
dc.identifier.urihttp://hdl.handle.net/1903/853
dc.description.abstractRecurrent neural networks have become popular models for system identification and time series prediction. NARX (Nonlinear AutoRegressive models with eXogenous inputs) neural network models are a popular subclass of recurrent networks and have beenused in many applications. Though embedded memory can be found in all recurrent network models, it is particularly prominent in NARX models. We show that using intelligent memory order selection through pruning and good initial heuristics significantly improves the generalization and predictive performance of these nonlinear systems on problems as diverse as grammatical inference and time series prediction. (Also cross-referenced as UMIACS-TR-96-77)en_US
dc.format.extent395874 bytes
dc.format.mimetypeapplication/postscript
dc.language.isoen_US
dc.relation.ispartofseriesUM Computer Science Department; CS-TR-3707en_US
dc.relation.ispartofseriesUMIACS; UMIACS-TR-96-77en_US
dc.titleA Delay Damage Model Selection Algorithm for NARX Neural Networksen_US
dc.typeTechnical Reporten_US
dc.relation.isAvailableAtDigital Repository at the University of Marylanden_US
dc.relation.isAvailableAtUniversity of Maryland (College Park, Md.)en_US
dc.relation.isAvailableAtTech Reports in Computer Science and Engineeringen_US
dc.relation.isAvailableAtUMIACS Technical Reportsen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record