Neural network for quadratic optimization with bound constraints
Neural network for quadratic optimization with bound constraints
复制标题
DOI：
10.1109/72.207617
复制
发表时间：
1993-03
影响因子：
--
通讯作者：
A. Bouzerdoum;T. Pattison
中科院分区：
文献类型：
--
作者：
A. Bouzerdoum;T. Pattison
提出了一种递归神经网络，它可以在每个优化变量上进行二次优化。证明了该网络是全局收敛的，并建立了二次问题和网络参数的条件，在此条件下，网络是指数渐近稳定的。通过适当地选择网络参数，对控制网络激励的微分方程组进行预处理，以降低其对噪声和循环误差的敏感性。所采用的神经网络的优化方法属于一般类的梯度法约束非线性优化，并与罚函数法相比，保证只产生可行的解决方案。
A recurrent neural network is presented which performs quadratic optimization subject to bound constraints on each of the optimization variables. The network is shown to be globally convergent, and conditions on the quadratic problem and the network parameters are established under which exponential asymptotic stability is achieved. Through suitable choice of the network parameters, the system of differential equations governing the network activations is preconditioned in order to reduce its sensitivity to noise and to roundoff errors. The optimization method employed by the neural network is shown to fall into the general class of gradient methods for constrained nonlinear optimization and, in contrast with penalty function methods, is guaranteed to yield only feasible solutions.