已为您找到该学者20条结果 成果回收站
【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
张雨浓, Y. Zhang and K. Chen
ELECTRONICS LETTERS 17th January 2008 Vol. 44 No. 2,-0001,():
-1年11月30日
The Wang neural network, together with its improved circuit implementation, could solve online a set of simultaneous linear equations. Global exponential convergence is presented for the Wang neural network, compared to the previously-presented asymptotical convergence. In addition, global stability results are presented for the Wang neural network. Illustrative examples further demonstrate the characteristics of the Wang neural network.
-
6浏览
-
0点赞
-
0收藏
-
0分享
-
43下载
-
0
-
引用
张雨浓, Y. Zhang, X. Lv, Z. Li, Z. Yang and H. Zhu
ELECTRONICS LETTERS 13th March 2008 Vol. 44 No. 6,-0001,():
-1年11月30日
A quadratic performance index is investigated for the online neural remedy for drift phenomenon of redundant robot manipulators. Computer simulations performed based on a three-link planar robot arm show the efficacy of such a quadratic-index based neural-remedy scheme.
-
47浏览
-
0点赞
-
0收藏
-
0分享
-
35下载
-
0
-
引用
张雨浓, Yunong Zhang *, Xuanjiao Lv, Zhonghua Li, Zhi Yang, Ke Chen
Mechatronics 18(2008)475-485,-0001,():
-1年11月30日
In this paper, a primal-dual neural network based on linear variational inequalities (LVI) is presented for the online repetitive motion planning of PA10 robot arm, a kinematically redundant manipulator. To do this, a drift-free criterion is exploited. In addition, the physical constraints such as joint limits and joint velocity limits are incorporated into the problem formulation of such a redundancy-resolution scheme. The scheme is finally reformulated as a quadratic-programming (QP) problem. As a QP real-time solver, the LVI-based primal-dual neural network is designed based on the QP-LVI conversion and Karush-Kuhn-Tucker (KKT) condition. With simple piecewise-linear dynamics and global exponential convergence to optimal solutions, it can handle general QP and linear programming (LP) problems in the same inverse-free manner. The repetitive motion planning scheme and the LVI-based primal-dual neural network are simulated successfully based on PA10 robot arm, with effectiveness demonstrated.
PA10 robot arm Repetitive motion planning Joint physical limits Quadratic-programming LVI-based primal-dual neural network
-
39浏览
-
0点赞
-
0收藏
-
0分享
-
50下载
-
0
-
引用
【期刊论文】梯度神经网络求解Sylvester方程之MATLAB仿真
张雨浓, 杨逸文, 陈轲, 蔡炳煌
系统仿真学报,2009,21(13): 4028~4031、4037,-0001,():
-1年11月30日
近年来,国内外学者发表了许多关于线性代数问题实时求解的方法,其中包括了矩阵求逆和线性方程组的并行求解方法。在研究了基于梯度法的递归神经网络用于Sylvester矩阵方程的实时求解后,通过使用Kronecker乘积和矩阵向量化等技术进行了MATLAB仿真从而验证了相关理论分析。计算机仿真的结果证实了这类神经网络方法在解决Sylvester矩阵方程中的有效性和高效率(特别是在使用幂S型激励函数的情况下)。
基于梯度法的递归神经网络, Sylvester方程, Kronecker乘积, 向量化, MATLAB 仿真
-
139浏览
-
0点赞
-
0收藏
-
0分享
-
110下载
-
0
-
引用