Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Design and Analysis of a General Recurrent Neural Network Model for Time-Varying Matrix Inversion
Zhang, Yunong; Ge, Shuzhi Sam
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.
Keyword(s): Hamilton Institute; Activation function; implicit dynamics; inverse kinematics; recurrent neural network (RNN); time-varying matrix; inversion
Publication Date:
2005
Type: Journal article
Peer-Reviewed: Yes
Institution: Maynooth University
Citation(s): Zhang, Yunong and Ge, Shuzhi Sam (2005) Design and Analysis of a General Recurrent Neural Network Model for Time-Varying Matrix Inversion. IEEE Transactions on Neural Networks, 16 (6). pp. 1477-1490. ISSN 1045-9227
Publisher(s): IEEE
File Format(s): application/pdf
Related Link(s): http://mural.maynoothuniversity.ie/2278/1/YZ_TNN-matrix-inversion-05.pdf
First Indexed: 2020-01-31 06:02:19 Last Updated: 2020-04-02 07:37:05