IEEE Trans Neural Netw Learn Syst. 2013 Feb;24(2):322-8. doi: 10.1109/TNNLS.2012.2223484.
In this brief, the quadratic problem with general linear constraints is reformulated using the Wolfe dual theory, and a very simple discrete-time recurrent neural network is proved to be able to solve it. Conditions that guarantee global convergence of this network to the constrained minimum are developed. The computational complexity of the method is analyzed, and experimental work is presented that shows its high efficiency.
在这份简要说明中，使用 Wolfe 对偶理论重新表述了具有一般线性约束的二次问题，并证明了一个非常简单的离散时间递归神经网络能够解决这个问题。本文还提出了保证该网络全局收敛到约束最小值的条件。分析了该方法的计算复杂性，并给出了实验工作，展示了其高效性。
