欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
不同于传统的梯度神经网络,一类特殊的用于解决时变问题（如时变矩阵求逆）的新型递归神经网络（ZNN）于2001年提出.为了便于使用数字电路进行硬件实现,需要将该类递归神经网络进行离散化,在之前工作的基础上,利用多点前向差分和中间差分数值微分方法,得到一类通过一系列ZNN离散模型表示的矩阵求逆方法,数学分析结果表明,传统牛顿迭代法可以看作其中一个特例.为验证此方法的有效性,针对定常矩阵求逆问题进行求解,同时,利用线搜索算法来保证该模型的收敛速度.实验结果表明,基于多种数值微分公式并辅以线搜索算法的ZNN离散模型可以较好地收敛到问题的理论解,且具有较佳的收敛性能.
英文摘要：
A special class of recurrent neural networks（ZNN）,different from the conventional gradient-based neural network,were proposed in 2001 for solving time-varying problems（e.g.time-varying matrix inversion）.For possible digital-circuit realization,such ZNN models need to be discretized.Based on the previous work,a method depicted by a series of discrete-time ZNN（DTZNN） models was proposed for matrix inversion by exploiting multiple-point forward-difference and central-difference formulas.Mathematical analysis shows that Newton iteration is actually a special case of DTZNN models.In order to verify the efficacy of the DTZNN models,these models are applied for constant matrix inversion.In addition,a line-search algorithm is employed to guarantee the convergence of such DTZNN models.Results show that the discrete-time ZNN models based on difference formulas and aided with line-search algorithm are effective on constant matrix inversion and have superior convergent performance.
同期刊论文项目
同项目期刊论文
A time-varying coefficient-based manipulability-maximizing scheme for motion control of redundant ro
Convergence analysis for the uncalibrated robotic hand-eye coordination based on the unmodeled dynam
Zhang neural network versus gradient-based neural network for time-varying linear matrix equation so
Different-Level Simultaneous Minimization of Joint-Velocity and Joint-Torque for Redundant Robot Man
Adaptive Fuzzy Control for Synchronization of Nonlinear Teleoperators with Stochastic Time-varying C
Solving for time-varying and static cube roots in real and complex domains via discrete-time ZD mode
Link between and Comparison and Combbination of Zhang Neural Network and Quasi-Newton BFGS Method fo
Different Complex ZFs Leading to Different Complex ZNN Models for TIme-Varing Complex Generalized In
Zhang Neural Network for Online SOlution of TIme-Varying LInear Matrix Inequality Aided With an Equa
A New Inequality-Based Obstacle-Avoidance MVN Scheme and Its Application to Redundant Robot Manipula
Posterior Cramer-Rao Lower Bounds for Target Tracking in Sensor Network With Quantized Range-Only Me
Dynamic Coupling Switching Control Incorporating Support Vector Machines for Wheeled Mobile Manipula
Adaptive Robust Coordinated Control of Multiple Mobile Manipulators Interacting with Rigid Environme
Design and experimentation of acceleration-level drift-free scheme aided by two recurrent neural net
Decentralized Adaptive Fuzzy Control of Coordinated Multiple Mobile Manipulators Interacting with No
Separated maneuvering target tracking algorithm along with three Cartesian coordinates for three-dim
Acceleration-Level Cyclic-Motion Generation of Constrained Redundant Robots Tracking Different Paths
Design and implementation of a zero-initial-velocity self-motion scheme on a six-DOF planar robot ma
Two/Infinity Norm Criteria Resolution of Manipulator Redundancy at Joint-Acceleration Level Using Pr
Different-level two-norm and infinity-norm minimization to remedy joint-torque instability/divergenc
Different-level redundancy-resolution and its equivalent relationship analysis for robot manipulator
Zhang neural network, Getz-Marsden dynamic system, and discrete-time algorithms for time-varying mat
Data fusion for target tracking in wireless sensor networks using quantized innovations and Kalman f
Neural-adaptive Output Control of a Class of Transportation Vehicles based on Wheeled Inverted Pendu
Integrating Color into the Local Features based on the Stable Color Invariant Regions for Image Retr
Effective parameter range for equivalence of velocity-level and acceleration-level redundancy resolu
Different Zhang functions leading to different Zhang-dynamics models illustrated via time-varying re
Comparison on Zhang neural dynamics and gradient-based neural dynamics for online solution of nonlin
Using GD to conquer the singularity problem of conventional controller for output tracking of nonlin
Acceleration-level repetitive motion planning of redundant planar robots solved by a simplified LVI-
Continuous-Time Solution Models and Verification of G-Type and ZG-Type ZPI of Time-Varying Complex M
Different Zhang functions resulting in different ZNN models demonstrated via time-varying linear mat
Different Zhang functions leading to different ZNN models illustrated via time-varying matrix square
Motion Synchronization of Bilateral Teleoperation Systems with Mode-dependent Time-varying Communica
Superior robustness of power-sum activation functions in Zhang neural networks for time-varying quad
Performance analysis of gradient neural network exploited for online time-varying quadratic minimiza
Common Nature of Learning Between Back-Propagation and Hopfield-Type Neural Networks for Generalized
Link Between and Comparison and Combination of Zhang Neural Network and Quasi-Newton BFGS Method for
Remedy scheme and theoretical analysis of joint-angle drift phenomenon for redundant robot manipulat
The link and comparison between velocity-level and acceleration-level repetitive motion planning sch
期刊信息
位置：