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

Authors:
Xiaolin Hu;Jun Wang
Affiliations:
Tsinghua National Lab of Information Science & Technology, State Key Lab of Intelligent Technology & Systems, and Department of Computer Science & Technology, Tsinghua University, Beijing, China 1 ...;Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, China
Venue:
Neural Information Processing
Year:
2007

Citing 9
Cited 0

On a Generalization of a Normal Map and Equation

SIAM Journal on Control and Optimization
On Convergence Conditions of an Extended Projection Neural Network

Neural Computation
On the Computational Power of Winner-Take-All

Neural Computation
A Recurrent Neural Network for Solving a Class of General Variational Inequalities

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Another K-winners-take-all analog neural network

IEEE Transactions on Neural Networks
A general projection neural network for solving monotone variational inequalities and related optimization problems

IEEE Transactions on Neural Networks
Solving Pseudomonotone Variational Inequalities and Pseudoconvex Optimization Problems Using the Projection Neural Network

IEEE Transactions on Neural Networks
A Simplified Dual Neural Network for Quadratic Programming With Its KWTA Application

IEEE Transactions on Neural Networks
Solving Generally Constrained Generalized Linear Variational Inequalities Using the General Projection Neural Networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.