Zhang neural network solving for time-varying full-rank matrix Moore–Penrose inverse

Authors:
Yunong Zhang;Yiwen Yang;Ning Tan;Binghuang Cai
Affiliations:
Sun Yat-sen University, School of Information Science & Technology, 510006, Guangzhou, China;Sun Yat-sen University, School of Information Science & Technology, 510006, Guangzhou, China;Sun Yat-sen University, School of Information Science & Technology, 510006, Guangzhou, China;Sun Yat-sen University, School of Information Science & Technology, 510006, Guangzhou, China
Venue:
Computing
Year:
2011

Citing 0
Cited 4

Letters: Zhang neural network versus gradient-based neural network for time-varying linear matrix equation solving

Neurocomputing
Time-varying moore-penrose inverse solving shows different zhang functions leading to different ZNN models

ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part I
Different ZFs leading to various ZNN models illustrated via online solution of time-varying underdetermined systems of linear equations with robotic application

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part II
Zhang-Gradient controllers of z0g0, z1g0 and z1g1 types for output tracking of time-varying linear systems with control-singularity conquered finally

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Zhang neural networks (ZNN), a special kind of recurrent neural networks (RNN) with implicit dynamics, have recently been introduced to generalize to the solution of online time-varying problems. In comparison with conventional gradient-based neural networks, such RNN models are elegantly designed by defining matrix-valued indefinite error functions. In this paper, we generalize, investigate and analyze ZNN models for online time-varying full-rank matrix Moore–Penrose inversion. The computer-simulation results and application to inverse kinematic control of redundant robot arms demonstrate the feasibility and effectiveness of ZNN models for online time-varying full-rank matrix Moore–Penrose inversion.