Finite time dual neural networks with a tunable activation function for solving quadratic programming problems and its application

In this paper, finite time dual neural networks with a new activation function are presented to solve quadratic programming problems. The activation function has two tunable parameters, which give more flexibility to design a neural network. By Lyapunov theorem, the finite-time stability can be derived for the proposed neural networks model, and the actual optimal solutions of the quadratic programming problems can be obtained in finite time interval. Different from the existing recurrent neural networks for solving the quadratic programming problems, the neural networks of this paper have a faster convergent speed, at the same time, reduced oscillation when delay appears, and less sensitivity to the additive noise with careful selection the parameters. The effectiveness of our methods are validated by theoretical analysis and numerical simulations.