论文信息 - Recurrent neural network for solving quadratic programming problems with equality constraints

Recurrent neural network for solving quadratic programming problems with equality constraints

A recurrent neural network for solving quadratic programming problems with equality constraints is presented. The proposed recurrent neural network is asymptotically stable and able to generate optimal solutions to quadratic programs with equality constraints. An opamp based analogue circuit realisation of the recurrent neural network is described. An illustrative example is also discussed to demonstrate the performance and characteristics of the analogue neural network.

J. Wang

[1] C H Chen. Neural networks in pattern recognition and their applications , 1991 .

[2] Jun Wang,et al. On the asymptotic Properties of Recurrent Neural Networks for Optimization , 1991, Int. J. Pattern Recognit. Artif. Intell..

[3] John J. Hopfield,et al. Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[4] David G. Luenberger,et al. Linear and nonlinear programming , 1984 .

[5] Jun Wang,et al. Electronic realisation of recurrent neural network for solving simultaneous linear equations , 1992 .

[6] G. Wilson. Quadratic programming analogs , 1986 .

[7] Leon O. Chua,et al. Neural networks for nonlinear programming , 1988 .