Related Experiment Videos
A class of finite-time dual neural networks for solving quadratic programming problems and its k-winners-take-all
Shuai Li1, Yangming Li, Zheng Wang
1Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA. lishuai8@gmail.edu
Abstract:
This paper presents a class of recurrent neural networks to solve quadratic programming problems. Different from most existing recurrent neural networks for solving quadratic programming problems, the proposed neural network model converges in finite time and the activation function is not required to be a hard-limiting function for finite convergence time. The stability, finite-time convergence property and the optimality of the proposed neural network for solving the original quadratic programming problem are proven in theory. Extensive simulations are performed to evaluate the performance of the neural network with different parameters. In addition, the proposed neural network is applied to solving the k-winner-take-all (k-WTA) problem. Both theoretical analysis and numerical simulations validate the effectiveness of our method for solving the k-WTA problem.
Related Concept Videos
Application of Nonlinear Inequalities
Quadratic Models
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Quadratic Equations
Statically Indeterminate Problem Solving
Mathematical Modeling: Problem Solving