已为您找到该学者20条结果 成果回收站
张雨浓, Yunong Zhang *, Zhan Li
Physics Letters A 373(2009)1639-1643,-0001,():
-1年11月30日
In this Letter, by following Zhang et al. is method, a recurrent neural network (termed as Zhang neural network, ZNN) is developed and analyzed for solving online the time-varying convex quadraticprogramming problem subject to time-varying linear-equality constraints. Different from conventional gradient-based neural networks (GNN), such a ZNN model makes full use of the time-derivative information of time-varying coefficient. The resultant ZNN model is theoretically proved to have global exponential convergence to the time-varying theoretical optimal solution of the investigated time-varying convex quadratic program. Computer-simulation results further substantiate the effectiveness, efficiency and novelty of such ZNN model and method.
Recurrent neural networks Time-varying Quadratic programming Global convergence Gradient-based neural network (, GNN),
-
50浏览
-
0点赞
-
0收藏
-
0分享
-
69下载
-
0
-
引用
【期刊论文】二次型最小化所展现的BP与Hopfield类型神经网络的学习同质性*
张雨浓, 麦剑章, 肖秀春, 李展, 易称福
《自动化应用技术》,2008,27(9):6~10、5,-0001,():
-1年11月30日
本论文揭示,作为两种并行的神经计算模型,BP和Hopfield类型神经网络都可以有效地对二次型V(x)=T/2+TVxxPxqx实现最小化求解。而且,尽管BP和Hopfield类型神经网络在网络设计思想和网络结构上呈现出很大的差异,但是它们在二次型函数最小化问题上都表现出了相同的学习能力,这说明两者具有本质的联系。
二次型函数最小化, BP 神经网络, Hopfield 类型神经网络, 学习同质性
-
59浏览
-
0点赞
-
0收藏
-
0分享
-
68下载
-
0
-
引用
【期刊论文】Legendre正交基前向神经网络的权值直接确定法
张雨浓, 张雨浓a, 刘巍b, 易称福a, 李巍a
大连海事件大学学报,2008,24(1):32~36,-0001,():
-1年11月30日
为避免权值反复迭代修正的冗长BP训练过程,避免传统方法陷入局部极小点,根据多项式理论,构造了一种新型前向神经网络模型,推导了基于最速下降法的误差反传算法和基于伪逆的直接确定法。仿真结果显示,迭代方法和伪逆直接确定法都能达到比较高的工作精度(10-6)。
正交多项式, Legendre 正交基, 标准BP算法, 伪逆
-
55浏览
-
0点赞
-
0收藏
-
0分享
-
66下载
-
0
-
引用
【期刊论文】一种权值直接确定及结构自适应的Chebyshev基函数神经网络
张雨浓, 陈裕隆, 姜孝华, 曾庆淡, 邹阿金,
计算机和科学,2009,36(6): 210~213,-0001,():
-1年11月30日
基于函数逼近理论,构造一种Chebyshev基函数神经网络模型。推导出该网络模型的权值直接确定方法,可一步计算出权值,克服了传统BP神经网络学习率选取困难、学习过程冗长和易陷入局部极小等缺点。在此基础上,设计了基于二分搜索的结构自适应算法,根据精度要求自动确定网络最优结构。理论分析及仿真验证均表明,该网络不仅能够快速地完成网络权值确定和结构自适应,且具有优异的学习与逼近能力,而且对随机加性噪声也具有较好的抑制作用。
神经网络, Chebyshev 正交基, 权值直接确定, 结构自适应确定
-
36浏览
-
0点赞
-
0收藏
-
0分享
-
62下载
-
0
-
引用
张雨浓, Yunong Zhang a, *, Weimu Maa, Xiao-Dong Li a, Hong-Zhou Tan a, Ke Chen b
Neurocomputing 72(2009)1679-1687,-0001,():
-1年11月30日
In view of parallel-processing nature and circuit-implementation convenience, recurrent neural networks are often employed to solve optimization problems. Recently, a primal-dual neural network based on linear variational inequalities (LVI) was developed by Zhang et al. for the online solution of linear-programming (LP) and quadratic-programming (QP) problems simultaneously subject to equality, inequality and bound constraints. For the final purpose of field programmable gate array (FPGA) and application-specific integrated circuit (ASIC) realization, we investigate in this paper the MATLAB Simulink modeling and simulative verification of such an LVI-based primal-dual neural network (LVI-PDNN). By using click-and-drag mouse operations in MATLAB Simulink environment, we could quickly model and simulate complicated dynamic systems. Modeling and simulative results substantiate the theoretical analysis and efficacy of the LVI-PDNN for solving online the linear and quadratic programs.
Neural networks Circuit implementation Linear programs Quadratic programs MATLAB Simulink modeling and simulation
-
91浏览
-
0点赞
-
0收藏
-
0分享
-
58下载
-
0
-
引用