A General Recurrent Neural Network Model for Time-Varying Matrix Inversion

Please use this identifier to cite or link to this item: https://doi.org/10.1109/CDC.2003.1272262

Title:	A General Recurrent Neural Network Model for Time-Varying Matrix Inversion
Authors:	Zhang, Y. Ge, S.S.
Issue Date:	2003
Citation:	Zhang, Y.,Ge, S.S. (2003). A General Recurrent Neural Network Model for Time-Varying Matrix Inversion. Proceedings of the IEEE Conference on Decision and Control 6 : 6169-6174. ScholarBank@NUS Repository. https://doi.org/10.1109/CDC.2003.1272262
Abstract:	This paper presents a general recurrent neural network model for online inversion of time-varying matrices. Utilizing the first-order time-derivative, the neural model guarantees its state trajectory globally converge to the exact inverse of a given time-varying matrix. In addition, exponential convergence can be achieved if linear or sigmoid activation function is used. Network sensitivity is also studied to show the desirable robustness property of this neural approach. Simulation results, including the application to kinematic control of redundant manipulators, are used to demonstrate the effectiveness and performance of the proposed neural model.
Source Title:	Proceedings of the IEEE Conference on Decision and Control
URI:	http://scholarbank.nus.edu.sg/handle/10635/68817
ISBN:	0780379241
ISSN:	01912216
DOI:	10.1109/CDC.2003.1272262
Appears in Collections:	Staff Publications

There are no files associated with this item.

Check