Robustness Analysis of a Power-Type Varying-Parameter Recurrent Neural Network for Solving Time-Varying QM and QP Problems and Applications
Robustness Analysis of a Power-Type Varying-Parameter Recurrent Neural Network for Solving Time-Varying QM and QP Problems and Applications
复制标题
DOI：
10.1109/tsmc.2018.2866843
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Zhijun Zhang;Lingdong Kong;Lunan Zheng;Pengchao Zhang;Xilong Qu;Bolin Liao;Zhuliang Yu
中科院分区：
文献类型：
--
作者：
Zhijun Zhang;Lingdong Kong;Lunan Zheng;Pengchao Zhang;Xilong Qu;Bolin Liao;Zhuliang Yu
变参数循环神经网络作为一种特殊的神经动力学方法，具有处理各种时变问题的强大能力，例如二次最小化（QM）和二次规划（QP）问题。本文提出了一种新型功率型变参数递归神经网络（PT-VP-RNN）来解决扰动时变 QM 和 QP 问题。首先，基于时变QM和QP问题的推广，详细介绍了PT-VP-RNN的设计过程。其次，对所提出的 PT-VP-RNN 的鲁棒性性能进行了理论分析和证明。更重要的是，模拟了两个数值例子来说明 PT-VP-RNN 即使在大扰动条件下的鲁棒收敛性能。最后，两个实际应用示例（即机器人跟踪示例和风险投资示例）进一步验证了所提出的 PT-VP-RNN 的有效性、准确性和广泛适用性。
Varying-parameter recurrent neural network, being a special kind of neural-dynamic methodology, has revealed powerful abilities to handle various time-varying problems, such as quadratic minimization (QM) and quadratic programming (QP) problems. In this paper, a novel power-type varying-parameter recurrent neural network (PT-VP-RNN) is proposed to solve the perturbed time-varying QM and QP problems. First, based on the generalization of time-varying QM and QP problems, the design process of the PT-VP-RNN is presented in detail. Second, the robustness performance of the proposed PT-VP-RNN is theoretically analyzed and proved. What is more, two numerical examples are simulated to illustrate the robustness convergence performance of PT-VP-RNN even in a large disturbance condition. Finally, two practical application examples (i.e., a robot tracking example and a venture investment example) further verify the effectiveness, accuracy, and widespread applicability of the proposed PT-VP-RNN.