School of Automation, Southeast University, Nanjing 210096, China.
Neural Netw. 2012 Feb;26:99-109. doi: 10.1016/j.neunet.2011.09.001. Epub 2011 Sep 16.
In this paper, a one-layer recurrent neural network is proposed for solving pseudoconvex optimization problems subject to linear equality and bound constraints. Compared with the existing neural networks for optimization (e.g., the projection neural networks), the proposed neural network is capable of solving more general pseudoconvex optimization problems with equality and bound constraints. Moreover, it is capable of solving constrained fractional programming problems as a special case. 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. Numerical examples with simulation results illustrate the effectiveness and characteristics of the proposed neural network. In addition, an application for dynamic portfolio optimization is discussed.
本文提出了一种用于求解带线性等式和边界约束的伪凸优化问题的单层递归神经网络。与现有的优化神经网络（例如投影神经网络）相比，所提出的神经网络能够解决更一般的带有等式和边界约束的伪凸优化问题。此外，它还能够解决约束分式规划问题作为特例。只要模型中设计的参数大于导出的下界，就可以保证所提出的神经网络的状态变量的收敛达到最优解。通过模拟结果的数值例子说明了所提出的神经网络的有效性和特点。此外，还讨论了一个用于动态投资组合优化的应用。
