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.
展开▼
