Document Detail


Convergence Study in Extended Kalman Filter-based Training of Recurrent Neural Networks.
MedLine Citation:
PMID:  21402512     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
Recurrent neural network (RNN) has emerged as a promising tool in modeling nonlinear dynamical systems, but the training convergence is still of concern. This paper aims to develop an effective extended Kalman filter-based RNN training approach with a controllable training convergence. The training convergence problem during extended Kalman filter-based RNN training has been proposed and studied by adapting two artificial training noise parameters: the covariance of measurement noise (R) and the covariance of process noise (Q) of Kalman filter. The R and Q adaption laws have been developed using the Lyapunov method and the maximum likelihood method, respectively. The effectiveness of the proposed adaption laws has been tested using a nonlinear dynamical benchmark system and further applied in cutting tool wear modeling. The results show that the R adaption law can effectively avoid the divergence problem and ensure the training convergence, whereas the Q adaption law helps improve the training convergence speed.
Authors:
Xiaoyu Wang; Yong Huang
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2011-3-10
Journal Detail:
Title:  IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council     Volume:  -     ISSN:  1941-0093     ISO Abbreviation:  -     Publication Date:  2011 Mar 
Date Detail:
Created Date:  2011-3-15     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101211035     Medline TA:  IEEE Trans Neural Netw     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Accelerating image registration with the Johnson-Lindenstrauss lemma: application to imaging 3-D neu...
Next Document:  Finite-Time Convergent Recurrent Neural Network with a Hard-Limiting Activation Function for Constra...