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

Xiaolin Hu, Jun Wang

Abstract

The k-winners-take-all (k-WTA) problem is to select k largest 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.
BibTeX
@inproceedings{hu2007solving,
  author = {Xiaolin Hu and Jun Wang},
  title = {{Solving the k-Winners-Take-All Problem and the Oligopoly Cournot-Nash Equilibrium Problem Using the General Projection Neural Networks}},
  booktitle = {ICONIP},
  year = {2007},
  doi = {10.1007/978-3-540-69158-7\_73},
}

Loading related content...

Figure