Abstract
In this paper, we first present some theoretical properties which include the convergence and bounds of both the trajectory and energy function for general neural network models for unconstrained nonconvex optimization problems. Based on this analysis, a novel time-delay neural network model is proposed for unconstrained nonconvex optimization. The simulation results of the new neural network on two examples indicate that the new neural network is quite efficient and outperforms the gradient neural network.
The first author was supported in part by grants from Hong Kong Baptist University (FRG) and General Research Fund (GRF) of Hong Kong. The second author was supported in part by the Chinese NSFC Grant (Nos. 11631013, 11331012 and 71331001) and the Key Project of Chinese National Programs for Fundamental Research and Development Grant (No. 2015CB856002).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Barzilai, J., Borwein, J.M.: Two-point step size gradient methods. IMA J. Numer. Anal. 8(1), 141–148 (1988)
Bouzerdoum, A., Pattison, T.R.: Neural network for quadratic optimization with bound constraints. IEEE Trans. Neural Netw. 4, 293–304 (1993)
Chen, Y.H., Fang, S.C.: Solving convex programming problem with equality constraints by neural networks. Comput. Math. Appl. 36, 41–68 (1998)
Cichocki, A., Unbehauen, R.: Neural Networks for Optimization and Signal Processing. Wiley, Stuttgart (1993)
Cichocki, A., Unbehauen, R., Weinzierl, K., Holzel, R.: A new neural network for solving linear programming problems. Eur. J. Oper. Res. 93, 244–256 (1996)
Chua, L.O., Lin, G.-N.: Nonlinear programming without computation. IEEE Trans. Circ. Syst. 31, 182–188 (1984)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational ability. Proc. Natl. Acad. Sci. 79, 2554–2558 (1982)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. 81, 3088–3092 (1984)
Hopfield, J.J., Tank, D.W.: Neural computation of decisions in optimization problems. Biol. Cybern. 52, 141–152 (1985)
Hou, Z.-G., Wu, C.-P., Bao, P.: A neural network for hierarchical optimization of nonlinear large-scale systems. Int. J. Syst. Sci. 29(2), 159–166 (1998)
Karmarkar, N.: A new polynomial-time algorithm for linear programming. Combinatorica 4, 373–395 (1984)
Kennedy, M.P., Chua, L.O.: Neural networks for nonlinear programming. IEEE Trans. Circ. Syst. 35, 554–562 (1988)
Liao, L.-Z., Qi, H.D., Qi, L.Q.: Neurodynamic optimization. J. Glob. Optim. 28, 175–195 (2004)
Lillo, W.E., Loh, M.-H., Hui, S., Żak, S.H.: On solving constrained optimization problems with neural networks: a penalty method approach. IEEE Trans. Neural Netw. 4, 931–940 (1993)
Maa, C.Y., Shanblatt, M.A.: Linear and quadratic programming neural network analysis. IEEE Trans. Neural Netw. 3(4), 580–594 (1992)
Maa, C.Y., Shanblatt, M.A.: A two-phase optimization neural network. IEEE Trans. Neural Netw. 3, 1003–1009 (1992)
Moré, J.J., Garbow, B.S., Hillstrom, K.E.: Testing unconstrained optimization software. ACM Trans. Math. Softw. 7, 17–41 (1981)
Qian X., Liao L.-Z., Sun J., Zhu H.: The convergent generalized central paths for linearly constrained convex programming. SIAM J. Optim. (2018) (to appear)
Rodríguez-Vázquez, A., Domínguez-Castro, R., Rueda, A., Huertas, J.L., Sánchez-Sinencio, E.: Nonlinear switched-capacitor ‘neural’ networks for optimization problems. IEEE Trans. Circ. Syst. 37, 384–398 (1990)
Tank, D.W., Hopfield, J.J.: Simple ‘neural’ optimization network: an A/D converter, signal decision circuit, and a linear programming circuit. IEEE Trans. Circ. Syst. 33, 533–541 (1986)
Wang, J.: Recurrent neural networks for computing pseudoinverses of rank-deficient matrices. SIAM J. Sci. Comput. 18, 1479–1493 (1997)
Wang, J., Xia, Y.: Analysis and design of primal-dual assignment networks. IEEE Trans. Neural Netw. 9, 183–194 (1998)
Wu, X.-Y., Xia, Y., Li, J., Chen, W.-K.: A high-performance neural network for solving linear and quadratic programming problems. IEEE Trans. Neural Netw. 7, 643–651 (1996)
Xia, Y.: A new neural network for solving linear and quadratic programming problems. IEEE Trans. Neural Netw. 7, 1544–1547 (1996)
Zak, S.H., Upatising, V., Lillo, W.E., Hui, S.: A dynamical systems approach to solving linear programming problems. In: Elworthy, K.D., Everitt, W.N., Lee, E.B. (eds.) Differential Equations, Dynamical Systems, and Control Science, pp. 913–946. Marcel Dekker, New York (1994)
Zak, S.H., Upatising, V., Hui, S.: Solving linear programming problems with neural networks: a comparative study. IEEE Trans. Neural Netw. 6, 94–104 (1995)
Zhang, H., Liu, Z., Huang, G.B., Wang, Z.: Novel weighting-delay-based stability criteria for recurrent neural networks with time-varying delay. Trans. Neural Netw. 21(1), 91–106 (2010)
Zhang, S., Constantinides, A.G.: Lagrange programming neural networks. IEEE Trans. Circ. Syst. 2 Analog Digital Sig. Process. 39, 441–452 (1992)
Zhang, S., Zhu, X., Zou, L.-H.: Second-order neural nets for constrained optimization. IEEE Trans. Neural Netw. 3, 1021–1024 (1992)
Zuo, Z., Yang, C., Wang, Y.: A new method for stability analysis of recurrent neural networks with interval time-varying delay. IEEE Trans. Neural Netw. 21(2), 339–344 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Liao, LZ., Dai, YH. (2018). A Time-Delay Neural Network Model for Unconstrained Nonconvex Optimization. In: Al-Baali, M., Grandinetti, L., Purnama, A. (eds) Numerical Analysis and Optimization. NAO 2017. Springer Proceedings in Mathematics & Statistics, vol 235. Springer, Cham. https://doi.org/10.1007/978-3-319-90026-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-90026-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-90025-4
Online ISBN: 978-3-319-90026-1
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)