A One-Layer Recurrent Neural Network for Solving Pseudoconvex Optimization with Box Set Constraints | Zendy

Huaiqin Wu | Zendy; Rong Yao | Zendy; Ruoxia Li | Zendy; Xiaowei Zhang | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

A One-Layer Recurrent Neural Network for Solving Pseudoconvex Optimization with Box Set Constraints

Author(s) -

Huaiqin Wu,

Rong Yao,

Ruoxia Li,

Xiaowei Zhang

Publication year - 2014

Publication title -

mathematical problems in engineering

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.262

H-Index - 62

eISSN - 1026-7077

pISSN - 1024-123X

DOI - 10.1155/2014/283092

Subject(s) - artificial neural network , correctness , constraint (computer aided design) , convergence (economics) , mathematical optimization , set (abstract data type) , domain (mathematical analysis) , computer science , layer (electronics) , mathematics , lyapunov function , feasible region , algorithm , artificial intelligence , nonlinear system , mathematical analysis , chemistry , physics , geometry , organic chemistry , quantum mechanics , economics , programming language , economic growth

A one-layer recurrent neural network is developed to solve pseudoconvex optimization with boxconstraints. Compared with the existing neural networks for solving pseudoconvex optimization, the proposed neuralnetwork has a wider domain for implementation. Based on Lyapunov stable theory, the proposed neural network isproved to be stable in the sense of Lyapunov. By applying Clarke’s nonsmooth analysis technique, the finite-time stateconvergence to the feasible region defined by the constraint conditions is also addressed. Illustrative examples furthershow the correctness of the theoretical results

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research