dc.contributor.author | Lin, Tsungnan | en_US |
dc.contributor.author | Giles, C. Lee | en_US |
dc.contributor.author | Horne, Bill G. | en_US |
dc.contributor.author | Kung, Sun-Yang | en_US |
dc.date.accessioned | 2004-05-31T22:42:05Z | |
dc.date.available | 2004-05-31T22:42:05Z | |
dc.date.created | 1996-12 | en_US |
dc.date.issued | 1998-10-15 | en_US |
dc.identifier.uri | http://hdl.handle.net/1903/853 | |
dc.description.abstract | Recurrent 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.extent | 395874 bytes | |
dc.format.mimetype | application/postscript | |
dc.language.iso | en_US | |
dc.relation.ispartofseries | UM Computer Science Department; CS-TR-3707 | en_US |
dc.relation.ispartofseries | UMIACS; UMIACS-TR-96-77 | en_US |
dc.title | A Delay Damage Model Selection Algorithm for NARX Neural Networks | en_US |
dc.type | Technical Report | en_US |
dc.relation.isAvailableAt | Digital Repository at the University of Maryland | en_US |
dc.relation.isAvailableAt | University of Maryland (College Park, Md.) | en_US |
dc.relation.isAvailableAt | Tech Reports in Computer Science and Engineering | en_US |
dc.relation.isAvailableAt | UMIACS Technical Reports | en_US |