Back to Search
Start Over
Recurrent Neural Networks Training With Stable Bounding Ellipsoid Algorithm.
- Source :
- IEEE Transactions on Neural Networks; Jun2009, Vol. 20 Issue 6, p983-991, 9p, 3 Diagrams, 4 Graphs
- Publication Year :
- 2009
-
Abstract
- Bounding ellipsoid (BE) algorithms offer an attractive alternative to traditional training algorithms for neural networks, for example, backpropagation and least squares methods. The benefits include high computational efficiency and fast convergence speed. In this paper, we propose an ellipsoid propagation algorithm to train the weights of recurrent neural networks for nonlinear systems identification. Both hidden layers and output layers can be updated. The stability of the BE algorithm is proven. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10459227
- Volume :
- 20
- Issue :
- 6
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Neural Networks
- Publication Type :
- Academic Journal
- Accession number :
- 42541134
- Full Text :
- https://doi.org/10.1109/TNN.2009.2015079