A One-Layer Recurrent Neural Network for Constrained Complex-Variable Convex Optimization

作者：Qin, Sitian; Feng, Jiqiang; Song, Jiahui; Wen, Xingnan; Xu, Chen^*

来源：IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(3): 534-544.

DOI：10.1109/TNNLS.2016.2635676

• Constrained complex-variable convex optimization
• convergence analysis
• one-layer recurrent neural network
• penalty method

In this paper, based on CR calculus and penalty method, a one-layer recurrent neural network is proposed for solving constrained complex-variable convex optimization. It is proved that for any initial point from a given domain, the state of the proposed neural network reaches the feasible region in finite time and converges to an optimal solution of the constrained complex-variable convex optimization finally. In contrast to existing neural networks for complex-variable convex optimization, the proposed neural network has a lower model complexity and better convergence. Some numerical examples and application are presented to substantiate the effectiveness of the proposed neural network.

• 出版日期2018-3
• 单位深圳大学; 哈尔滨工业大学