|
DRUM >
College of Computer, Mathematical & Natural Sciences >
Computer Science >
Technical Reports from UMIACS >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1903/853
|
| Title: | A Delay Damage Model Selection Algorithm for NARX Neural Networks |
| Authors: | Lin, Tsungnan
Giles, C. Lee
Horne, Bill G.
Kung, Sun-Yang |
| Type: | Technical Report |
| Issue Date: | 15-Oct-1998 |
| Series/Report no.: | UM Computer Science Department; CS-TR-3707
UMIACS; UMIACS-TR-96-77 |
| 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) |
| URI: | http://hdl.handle.net/1903/853 |
| Appears in Collections: | Technical Reports of the Computer Science Department
Technical Reports from UMIACS
|
All items in DRUM are protected by copyright, with all rights reserved.
|
