A one-layer recurrent neural network for non-smooth convex optimization subject to linear inequality constraints

• Published in: Chaos, solitons and fractals Vol. 87; pp. 39 - 46
• Main Authors: Liu, Xiaolan, Zhou, Mi
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.06.2016
• Subjects: Finite-time convergence; Linear inequality constraints; Lower bounds; Neural network; Non-smooth analysis; Lower bounds; 90C25; 90C33; Non-smooth analysis; Linear inequality constraints; Neural network; Finite-time convergence
• ISSN: 0960-0779; 1873-2887
• DOI: 10.1016/j.chaos.2016.03.009

In this paper, a one-layer recurrent network is proposed for solving a non-smooth convex optimization subject to linear inequality constraints. Compared with the existing neural networks for optimization, the proposed neural network is capable of solving more general convex optimization with linear inequality constraints. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed as long as the designed parameters in the model are larger than the derived lower bounds.