## Analysis and Design of a $k$ -Winners-Take-All Model With a Single State Variable and the Heaviside Step Activation Function

- Jun Wang
- IEEE Transactions on Neural Networks
- 2010

Highly Influenced

@article{Xia2009ANN, title={A novel neural dynamical approach to convex quadratic program and its efficient applications}, author={Youshen Xia and Changyin Sun}, journal={Neural networks : the official journal of the International Neural Network Society}, year={2009}, volume={22 10}, pages={1463-70} }

- Published 2009 in Neural Networks
DOI:10.1016/j.neunet.2009.03.020

This paper proposes a novel neural dynamical approach to a class of convex quadratic programming problems where the number of variables is larger than the number of equality constraints. The proposed continuous-time and proposed discrete-time neural dynamical approach are guaranteed to be globally convergent to an optimal solution. Moreover, the number of its neurons is equal to the number of equality constraints. In contrast, the number of neurons in existing neural dynamical methods is atâ€¦Â CONTINUE READING