Convergence properties of recurrent neural network
58 p.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Theses and Dissertations |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/46994 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| id |
sg-ntu-dr.10356-46994 |
|---|---|
| record_format |
dspace |
| spelling |
sg-ntu-dr.10356-469942023-07-04T15:32:34Z Convergence properties of recurrent neural network Fei, Yong Gang Song Qing School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering 58 p. Elman networks (ENs) can be viewed as a feed-forward (FF) neural network with an additional set of inputs from the context layer input (feedback from the hidden layer). Therefore, a standard on-line (real time) back propagation (BP) algorithm, instead of the off-line back propagation through time (BPTT) algorithm, can be applied for the training of ENs, which is usually called Elman back propagation (EBP) for discrete time sequence prediction applications. However, the standard BP training algorithm is not the most suitable one for ENs. Using a small learning rate may help improve the training of ENs, but it can result in very slow convergence speed and poor generalization performance, while a large learning rate may lead to unstable training in terms of weight divergence. Master of Science (Computer Control and Automation) 2011-12-27T05:52:57Z 2011-12-27T05:52:57Z 2010 2010 Thesis http://hdl.handle.net/10356/46994 Nanyang Technological University application/pdf |
| institution |
Nanyang Technological University |
| building |
NTU Library |
| continent |
Asia |
| country |
Singapore Singapore |
| content_provider |
NTU Library |
| collection |
DR-NTU |
| topic |
DRNTU::Engineering::Electrical and electronic engineering |
| spellingShingle |
DRNTU::Engineering::Electrical and electronic engineering Fei, Yong Gang Convergence properties of recurrent neural network |
| description |
58 p. |
| author2 |
Song Qing |
| author_facet |
Song Qing Fei, Yong Gang |
| format |
Theses and Dissertations |
| author |
Fei, Yong Gang |
| author_sort |
Fei, Yong Gang |
| title |
Convergence properties of recurrent neural network |
| title_short |
Convergence properties of recurrent neural network |
| title_full |
Convergence properties of recurrent neural network |
| title_fullStr |
Convergence properties of recurrent neural network |
| title_full_unstemmed |
Convergence properties of recurrent neural network |
| title_sort |
convergence properties of recurrent neural network |
| publishDate |
2011 |
| url |
http://hdl.handle.net/10356/46994 |
| _version_ |
1772825404275425280 |