Hu Xiaolin, Zhang Bo
State Key Laboratory of Intelligent Technology & Systems, TNList, and Department of Computer Science & Technology, Tsinghua University, Beijing, China.
IEEE Trans Syst Man Cybern B Cybern. 2009 Dec;39(6):1640-5. doi: 10.1109/TSMCB.2009.2025700. Epub 2009 Aug 4.
There exist many recurrent neural networks for solving optimization-related problems. In this paper, we present a method for deriving such networks from existing ones by changing connections between computing blocks. Although the dynamic systems may become much different, some distinguished properties may be retained. One example is discussed to solve variational inequalities and related optimization problems with mixed linear and nonlinear constraints. A new network is obtained from two classical models by this means, and its performance is comparable to its predecessors. Thus, an alternative choice for circuits implementation is offered to accomplish such computing tasks.
存在许多用于解决与优化相关问题的递归神经网络。在本文中，我们提出了一种通过改变计算块之间的连接从现有网络中推导此类网络的方法。尽管动态系统可能会变得大不相同，但一些显著特性可能会保留下来。讨论了一个用于解决具有混合线性和非线性约束的变分不等式及相关优化问题的例子。通过这种方式从两个经典模型中获得了一个新网络，其性能与它的前身相当。因此，为完成此类计算任务提供了一种电路实现的替代选择。
