A Finite-Time Recurrent Neural Network for Computing Quadratic Minimization with Time-Varying Coefficients

XIAO Lin; LU Rongbo

doi:10.1049/cje.2019.01.009

Volume 28 Issue 2

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2019 > 28(2): 253-258

XIAO Lin and LU Rongbo, “A Finite-Time Recurrent Neural Network for Computing Quadratic Minimization with Time-Varying Coefficients,” Chinese Journal of Electronics, vol. 28, no. 2, pp. 253-258, 2019, doi: 10.1049/cje.2019.01.009

Citation:

XIAO Lin and LU Rongbo, “A Finite-Time Recurrent Neural Network for Computing Quadratic Minimization with Time-Varying Coefficients,” Chinese Journal of Electronics, vol. 28, no. 2, pp. 253-258, 2019, doi: 10.1049/cje.2019.01.009

Citation:

PDF( 571 KB)

A Finite-Time Recurrent Neural Network for Computing Quadratic Minimization with Time-Varying Coefficients

doi: 10.1049/cje.2019.01.009

XIAO Lin,
LU Rongbo

College of Information Science and Engineering, Jishou University, Jishou 416000, China

Funds: This work is supported by the National Natural Science Foundation of China (No.61866013, No.61503152, No.61563017, No.61662025, No.61363033), the Natural Science Foundation of Hunan Province, China (No.2019JJ50478, No.2016JJ2101), and the Research Foundation of Education Bureau of Hunan Province, China (No.15B192).

Received Date: 2016-04-18
Rev Recd Date: 2016-10-22
Publish Date: 2019-03-10

Abstract

Abstract

This paper proposes a Finite-time Zhang neural network (FTZNN) to solve time-varying quadratic minimization problems. Different from the original Zhang neural network (ZNN) that is specially designed to solve time-varying problems and possesses an exponential convergence property, the proposed neural network exploits a sign-bi-power activation function so that it can achieve the finite-time convergence. In addition, the upper bound of the finite convergence time for the FTZNN model is analytically estimated in theory. For comparative purposes, the original ZNN model is also presented to solve time-varying quadratic minimization problems. Numerical experiments are performed to evaluate and compare the performance of the original ZNN model and the FTZNN model. The results demonstrate that the FTZNN model is a more effective solution model for solving time-varying quadratic minimization problems.
- Recurrent neural network,
- Quadratic minimization,
- Activation function,
- Finite-time convergence,
- Comparative verification

FullText(HTML)

References(16)

References

R. Fantacci, M. Forti, M. Marini, et al., “A neural network for constrained optimization with application to CDMA communication systems”, IEEE Transactions on Circuits and Systems Ⅱ: Analog and Digital Signal Processing, Vol.50, No.8, pp.484-487, 2003.

Y. Zhang and Z. Li, “Zhang neural network for online solution of time-varying convex quadratic program subject to time-varying linear-equality constraints”, Physics Letters A, Vol.373, No.18, pp.1639-1643, 2009.

L. Jin and Y. Zhang, “Discrete-time Zhang neural network for online time-varying nonlinear optimization with application to manipulator motion generation”, IEEE Transactions on Neural Networks and Learning Systems, Vol.26, No.7, pp.1525-1531, 2015.

Y. Ye and S. Zhang, “New results on quadratic minimization”, SIAM Journal on Optimization, Vol.14, No.1, pp.245-267, 2003.

G. Lee, N. Tam and N. Yen, “Stability of linear-quadratic minimization over Euclidean balls”, SIAM Journal on Optimization, Vol.22, No.3, pp.936-952, 2003.

Y. Zhang, B. Mu and H. Zheng, “Link between and comparison and combination of Zhang neural network and quasi-Newton BFGS method for time-varying quadratic minimization”, IEEE Transactions on Cybernetics, Vol.43, No.2, pp.490-5032013.

X. Yang, A. Shen, J. Yang, et al., “Artificial neural network based Trilogic SVM control in current source rectifier”, Chinese Journal of Electronics, Vol.23, No.4, pp.723-728, 2014.

L. Xiao, “A nonlinearly activated neural dynamics and its finite-time solution to time-varying nonlinear equation”, Neurocomputing, Vol.173, pp.1983-1988, 2016.

H. Sun, T. Yuan, X. Li, et al., “Accelerometer-based gait authentication via neural network”, Chinese Journal of Electronics, Vol.21, No.3, pp.481-484, 2012.

F. Ding and T. Chen, “Gradient based iterative algorithms for solving a class of matrix equations”, IEEE Transactions on Automatic Control, Vol.50, No.8, pp.1216-1221, 2005.

B. Zhou, G. Duan and Z. Li, “Gradient based iterative algorithm for solving coupled matrix equations”, System Control Letters, Vol.58, pp.327-333, 2009

D. Guo, C. Yi and Y. Zhang, “Zhang neural network versus gradient-based neural network for time-varying linear matrix equation solving”, Neurocomputing, Vol.74, pp.3708-3712, 2011.

L. Xiao, “A nonlinearly-activated neurodynamic model and its finite-time solution to equality-constrained quadratic optimization with nonstationary coefficients”, Applied Soft Computing, Vol.40, pp.252-259, 2016.

S. Li, S. Chen and B. Liu, “Accelerating a recurrent neural network to finite-time convergence for solving timevarying Sylvester equation by using a sign-bi-power activation function”, Neural Processing Letters, Vol.37, pp.189-205, 2013.

L. Xiao and R. Lu, “Finite-time solution to nonlinear equation using recurrent neural dynamics with a specially-constructed activation function”, Neurocomputing, Vol.151, pp.246-251, 2015.

P. Miao, Y. Shen, Y. Huang, et al., “Solving timevarying quadratic programs based on finite-time Zhang neural networks and their application to robot tracking”, Neural Computing and Applications, Vol.26, No.3, pp.693-703, 2015.

Relative Articles

Supplements(0)

Cited By

Proportional views