Back to Search
Start Over
Improved Computation for Levenberg-Marquardt Training.
- Source :
- IEEE Transactions on Neural Networks; Jun2010, Vol. 21 Issue 6, p930-937, 8p
- Publication Year :
- 2010
-
Abstract
- The improved computation presented in this paper is aimed to optimize the neural networks learning process using Levenberg-Marquardt (LM) algorithm. Quasi-Hessian matrix and gradient vector are computed directly, without Jacobian matrix multiplication and storage. The memory limitation problem for LM training is solved. Considering the symmetry of quasi-Hessian matrix, only elements in its upper/lower triangular array need to be calculated. Therefore, training speed is improved significantly, not only because of the smaller array stored in memory, but also the reduced operations in quasi-Hessian matrix calculation. The improved memory and time efficiencies are especially true for large sized patterns training. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10459227
- Volume :
- 21
- Issue :
- 6
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Neural Networks
- Publication Type :
- Academic Journal
- Accession number :
- 51308465
- Full Text :
- https://doi.org/10.1109/TNN.2010.2045657