Recurrent Neural Network Model Based on Projective Operator and Its Application to Optimization Problems

MA Ru-ning; CHEN Tian-ping

Article Contents

Article Navigation > Applied Mathematics and Mechanics > 2006 > 27(4): 484-494

MA Ru-ning, CHEN Tian-ping. Recurrent Neural Network Model Based on Projective Operator and Its Application to Optimization Problems[J]. Applied Mathematics and Mechanics, 2006, 27(4): 484-494.

Citation:

MA Ru-ning, CHEN Tian-ping. Recurrent Neural Network Model Based on Projective Operator and Its Application to Optimization Problems[J]. Applied Mathematics and Mechanics, 2006, 27(4): 484-494.

Citation:

MA Ru-ning, CHEN Tian-ping. Recurrent Neural Network Model Based on Projective Operator and Its Application to Optimization Problems[J]. Applied Mathematics and Mechanics, 2006, 27(4): 484-494.

PDF( 434 KB)

Recurrent Neural Network Model Based on Projective Operator and Its Application to Optimization Problems

MA Ru-ning^1,2,
CHEN Tian-ping²

1.
Department of Mathematics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, P. R. China;

Received Date: 2004-03-24
Rev Recd Date: 2006-01-10
Publish Date: 2006-04-15

Abstract

Abstract

The recurrent neural network (RNN) model based on projective operator is studied.Different from the former study,the value region of projective operator in the neural network which they study was a general closed convex subset of n demensional Euclidean space and it wasn't a compact convex set in general,that is,the value region of projective operator was probably unbounded.They prove that the network has a global solution and its solution trajectory converges to some equilibrium set whenever objective function satisfies some conditions.After that,the model was applied to continuously differentiable optimization and nonlinear or implicit complementarity problems.In addition,simulation experiments confirm the efficiency of the RNN.
- recurrent neural network model,
- projective operator,
- global convergence,
- optimization,
- complementarity problem

FullText(HTML)

References(15)

References

[1]	Hopfield J J,Tank D W.Neural computation of decision in optimization problem[J].Biol Cybern,1985,52(1):141—152.
[2]	Tank D W,Hopfield J J.Simple ‘neural’ optimization networks: an A/D converter, signal decision circuit, and a linear programming circuit[J].IEEE Trans Circuits Syst (Ⅰ),1988,35(5):554—562. doi: 10.1109/31.1783
[3]	Bouzerdoum A,Pattison T R.Neural network for quadratic optimization with bound constraints[J].IEEE Transactions on Neural Networks,1993,4(2):293—303. doi: 10.1109/72.207617
[4]	Perez-Ilzarbe M J.Convergence analysis of a discrete-time recurrent neural network to perform quadratic real optimization with bound constraints[J].IEEE Transactions on Neural Networks,1998,9(6):1344—1351. doi: 10.1109/72.728385
[5]	Liang X B,Wang J.A recurrent neural network for nonlinear optimization with a continuosly differentiable objective function and bound constraints[J].IEEE Transactions on Neural Networks,2000,11(6):1251—1262. doi: 10.1109/72.883412
[6]	XIA You-shen,Leung Henry,WANG Jun.A projection neural network and its application to constrained optimization problems[J].IEEE Trans Circuits Syst (Ⅰ),2002,49(4):447—458. doi: 10.1109/81.995659
[7]	XIA You-shen,WANG Jun.A recurrent neural network for solving linear projection equations[J].Neural Networks,2000,13(3):337—350. doi: 10.1016/S0893-6080(00)00019-8
[8]	Liang X B.A recurrent neural network for nonlinear continuously differentiable optimization over a compact convex subset[J].IEEE Transactions on Neural Networks,2001,12(6):1487—1490. doi: 10.1109/72.963784
[9]	Liang X B.Qualitative analysis of a recurrent neural network for nonlinear continuously differentiable convex minimization over a nonempty closed convex subset[J].IEEE Transactions on Neural Networks,2001,12(6):1521—1525. doi: 10.1109/72.963790
[10]	Kinderlehrer D,Stampcchia G.An Introduction to Variational Inequalities and Their Applications[M].New York:Academic,1980.
[11]	Courant R,John F.Introduction to Calculus and Analysis[M].Vol 1.New York:Wiley,1989.
[12]	Fischer A.An NCP-function and its use for the solution of complementarity problems[A]In:Du D,Qi L,Womersley R,Eds.Recent Advance in Nonsmooth Optimization[C].New Jersey:World Scientific Publishers,1995,88—105.
[13]	Fischer A.New constrained optimization reformulation of complementarity problems[J].Journal of Optimization Theory and Applications,1998,97(1):105—117. doi: 10.1023/A:1022627217515
[14]	Qi H,Liao L.A smoothing Newton method for general nonlinear complementarity problems[J].Computational Optimization Applications,2000,17(2/3):231—253. doi: 10.1023/A:1026554432668
[15]	Kojima M,Shindo S.Extensions of Newton and quasi-Newton methods to systems of PC1 equations[J].J Oper Res Soc Jpn,1986,29:352—374.