论文信息 - Lagrange Neural Networks for Linear Programming

Lagrange Neural Networks for Linear Programming

Abstract A new artificial neural model for linear programming is presented. The model is globally stable and can provide optimal solution from arbitrary initial states. Applications to optimal linear classifiers (adaptive threshold elements) are discussed in detail.

Anthony G. Constantinides | Shengwei Zhang | Xianing Zhu

[1] Herbert Fischer. Automatic differentiation: parallel computation of function, gradient, and Hessian matrix , 1990, Parallel Comput..

[2] Narendra Karmarkar,et al. A new polynomial-time algorithm for linear programming , 1984, Comb..

[3] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[4] Wr Jeffrey,et al. Neural network processing as a tool for function optimization , 1987 .

[5] FRED W. SMITH,et al. Pattern Classifier Design by Linear Programming , 1968, IEEE Transactions on Computers.

[6] Dimitri P. Bertsekas,et al. Constrained Optimization and Lagrange Multiplier Methods , 1982 .

[7] Bernard Widrow,et al. Neural nets for adaptive filtering and adaptive pattern recognition , 1988, Computer.

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

[9] Terence D. Sanger,et al. Optimal unsupervised learning in a single-layer linear feedforward neural network , 1989, Neural Networks.

[10] John C. Platt,et al. Analog decoding using neural networks , 1987 .