Please use this identifier to cite or link to this item: https://doi.org/10.1109/TNN.2005.857946
Title: Design and analysis of a general recurrent neural network model for time-varying matrix inversion
Authors: Zhang, Y. 
Ge, S.S. 
Keywords: Activation function
Implicit dynamics
Inverse kinematics
Recurrent neural network (RNN)
Time-varying matrix inversion
Issue Date: Nov-2005
Citation: Zhang, Y., Ge, S.S. (2005-11). Design and analysis of a general recurrent neural network model for time-varying matrix inversion. IEEE Transactions on Neural Networks 16 (6) : 1477-1490. ScholarBank@NUS Repository. https://doi.org/10.1109/TNN.2005.857946
Abstract: Following the idea of using first-order time derivatives, this paper presents a general recurrent neural network (RNN) model for online inversion of time-varying matrices. Different kinds of activation functions are investigated to guarantee the global exponential convergence of the neural model to the exact inverse of a given time-varying matrix. The robustness of the proposed neural model is also studied with respect to different activation functions and various implementation errors. Simulation results, including the application to kinematic control of redundant manipulators, substantiate the theoretical analysis and demonstrate the efficacy of the neural model on time-varying matrix inversion, especially when using a power-sigmoid activation function. © 2005 IEEE.
Source Title: IEEE Transactions on Neural Networks
URI: http://scholarbank.nus.edu.sg/handle/10635/55531
ISSN: 10459227
DOI: 10.1109/TNN.2005.857946
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

204
checked on Jul 17, 2018

WEB OF SCIENCETM
Citations

172
checked on Jun 20, 2018

Page view(s)

190
checked on Jul 20, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.