An Inertial Projection Neural Network for Solving Variational Inequalities

An Inertial Projection Neural Network for Solving Variational Inequalities
复制标题

用于求解变分不等式的惯性投影神经网络

DOI:
10.1109/tcyb.2016.2523541
复制
发表时间:
2017-03
影响因子:
11.8
通讯作者:
Li Chaojie
Li Chaojie
中科院分区:
计算机科学1区
文献类型:
--
作者:
He Xing;Huang Tingwen;Yu Junzhi;Li Chu;ong;Li Chaojie

文献摘要

参考文献

被引文献

相似文献

最近,投影神经网络(PNN)被提出用于求解单调变分不等式(VIS)及相关的凸优化问题。本文将惯性项考虑到一阶PNN中,提出了一种求解VIS的惯性PNN(IPNN)。在一定条件下,IPNN被证明是稳定的,并且可以用于解决与可视化相关的更广泛的约束优化问题。与已有的神经网络相比,惯性项的存在克服了许多基于最速下降法构造的神经网络的一些缺点,更便于探索非凸优化问题的不同Karush-Kuhn-Tucker最优解。最后,三个数值算例的仿真结果表明了所提出的神经网络的有效性和性能。
Recently, projection neural network (PNN) was proposed for solving monotone variational inequalities (VIs) and related convex optimization problems. In this paper, considering the inertial term into first order PNNs, an inertial PNN (IPNN) is also proposed for solving VIs. Under certain conditions, the IPNN is proved to be stable, and can be applied to solve a broader class of constrained optimization problems related to VIs. Compared with existing neural networks (NNs), the presence of the inertial term allows us to overcome some drawbacks of many NNs, which are constructed based on the steepest descent method, and this model is more convenient for exploring different Karush–Kuhn–Tucker optimal solution for nonconvex optimization problems. Finally, simulation results on three numerical examples show the effectiveness and performance of the proposed NN.
解决二层线性规划问题的循环神经网络
DOI: 10.1109/tnnls.2013.2280905
发表时间: 2014-04
影响因子: 10.4
作者:
He Xing;Li Chu;ong;Huang Tingwen;Li Chaojie;Huang Junjian
通讯作者: Huang Junjian
DOI: 10.1007/b97543
发表时间: 2003
期刊: --
影响因子: --
作者:
F. Facchinei;J. Pang
通讯作者: F. Facchinei;J. Pang
DOI: 10.1016/j.neunet.2014.12.007
发表时间: 2015-03
期刊: Neural networks : the official journal of the International Neural Network Society
影响因子: --
作者:
Sitian Qin;Dejun Fan;Guangxi Wu;Lijun Zhao
通讯作者: Sitian Qin;Dejun Fan;Guangxi Wu;Lijun Zhao
DOI: 10.1109/tsmcb.2006.886166
发表时间: 2007-06
期刊: IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
影响因子: --
作者:
Xiaolin Hu;Jun Wang
通讯作者: Xiaolin Hu;Jun Wang
DOI: 10.1140/epjb/e2004-00327-2
发表时间: 2004-10
期刊: The European Physical Journal B - Condensed Matter and Complex Systems
影响因子: --
作者:
Chunguang Li;Guangrong Chen;X. Liao;Juebang Yu
通讯作者: Chunguang Li;Guangrong Chen;X. Liao;Juebang Yu