Robustness analysis of a hybrid of recursive neural dynamics for online matrix inversion

Robustness analysis of a hybrid of recursive neural dynamics for online matrix inversion

0.00 Avg rating0 Votes
Article ID: iaor201530233
Volume: 273
Start Page Number: 969
End Page Number: 975
Publication Date: Jan 2016
Journal: Applied Mathematics and Computation
Authors: ,
Keywords: neural networks, programming: dynamic, matrices, simulation
Abstract:

Encouraged by superior convergence performance achieved by a recently‐proposed hybrid of recursive neural dynamics for online matrix inversion, we investigate its robustness properties in this paper when there exists large model implementation errors. Theoretical analysis shows that the perturbed dynamic system is still global stable with the tight steady‐state bound of solution error estimated. Moreover, this paper analyses global exponential convergence rate and finite convergence time of such a hybrid dynamical model to a relatively loose solution error bound. Computer simulation results substantiate our analysis on the perturbed hybrid neural dynamics for online matrix inversion when having large implementation errors.

Reviews

Required fields are marked *. Your email address will not be published.