Solving the k-Winners-Take-All Problem and the Oligopoly Cournot-Nash Equilibrium Problem Using the General Projection Neural Networks

The k-winners-take-all (k-WTA) problem is to select klargest inputs from a set of inputs in a network, which has many applications in machine learning. The Cournot-Nash equilibrium is an important problem in economic models . The two problems can be formulated as linear variational inequalities (LVIs). In the paper, a linear case of the general projection neural network (GPNN) is applied for solving the resulting LVIs, and consequently the two practical problems. Compared with existing recurrent neural networks capable of solving these problems, the designed GPNN is superior in its stability results and architecture complexity.

[1]  Xiaolin Hu,et al.  A Recurrent Neural Network for Solving a Class of General Variational Inequalities , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  Wolfgang Maass,et al.  On the Computational Power of Winner-Take-All , 2000, Neural Computation.

[3]  Corneliu A. Marinov,et al.  Stable computational dynamics for a class of circuits with O(N) interconnections capable of KWTA and rank extractions , 2005, IEEE Transactions on Circuits and Systems I: Regular Papers.

[4]  Corneliu A. Marinov,et al.  Another K-winners-take-all analog neural network , 2000, IEEE Trans. Neural Networks Learn. Syst..

[5]  A. Nagurney,et al.  Projected Dynamical Systems and Variational Inequalities with Applications , 1995 .

[6]  J. Pang,et al.  On a Generalization of a Normal Map and Equation , 1995 .

[7]  F. Facchinei,et al.  Finite-Dimensional Variational Inequalities and Complementarity Problems , 2003 .

[8]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[9]  Gang Feng,et al.  On Convergence Conditions of an Extended Projection Neural Network , 2005, Neural Computation.

[10]  Xiaolin Hu,et al.  Solving Pseudomonotone Variational Inequalities and Pseudoconvex Optimization Problems Using the Projection Neural Network , 2006, IEEE Transactions on Neural Networks.

[11]  Edgar Sanchez-Sinencio,et al.  Nonlinear switched capacitor 'neural' networks for optimization problems , 1990 .

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

[13]  Jinde Cao,et al.  A high performance neural network for solving nonlinear programming problems with hybrid constraints , 2001 .

[14]  Xiaolin Hu,et al.  Solving Generally Constrained Generalized Linear Variational Inequalities Using the General Projection Neural Networks , 2007, IEEE Transactions on Neural Networks.

[15]  Jun Wang,et al.  A projection neural network and its application to constrained optimization problems , 2002 .

[16]  Shubao Liu,et al.  A Simplified Dual Neural Network for Quadratic Programming With Its KWTA Application , 2006, IEEE Transactions on Neural Networks.

[17]  William J. Wolfe,et al.  K-winner networks , 1991, IEEE Trans. Neural Networks.

[18]  Jun Wang,et al.  A general projection neural network for solving monotone variational inequalities and related optimization problems , 2004, IEEE Transactions on Neural Networks.