These tools will no longer be maintained as of December 31, 2024. Archived website can be found here. PubMed4Hh GitHub repository can be found here. Contact NLM Customer Service if you have questions.


Pubmed for Handhelds

PUBMED FOR HANDHELDS

Search MEDLINE/PubMed

  • Title: Recurrent neural networks training with stable bounding ellipsoid algorithm.
    Author: Yu W, de Jesús Rubio J.
    Journal: IEEE Trans Neural Netw; 2009 Jun; 20(6):983-91. PubMed ID: 19447727.
    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] [Full Text] [Related] [New Search]