Results 271 to 280 of about 8,474,325 (290)
Some of the next articles are maybe not open access.
Convergence of a Finite-Time Zhang Neural Network for Moore–Penrose Matrix Inversion
2021Moore-Penrose or pseudo inverse is examined for a time varying matrix. The Finite time model for Moore-Penrose left and right inverse is proposed and investigated. Infinite time for convergence in the original Zhang network is said to converge in finite time when the proposed Finite time Moore-Penrose inverse is employed. Nonlinear activation functions
G. Sowmya, P. Thangavel
openaire +1 more source
2009
A special kind of recurrent neural networks (RNN) with implicit dynamics has recently been proposed by Zhang et al , which could be generalized to solve online various time-varying problems. In comparison with conventional gradient neural networks (GNN), such RNN (or termed specifically as Zhang neural networks, ZNN) models are elegantly designed by ...
Yunong Zhang, Yiwen Yang, Ning Tan 0003
openaire +2 more sources
A special kind of recurrent neural networks (RNN) with implicit dynamics has recently been proposed by Zhang et al , which could be generalized to solve online various time-varying problems. In comparison with conventional gradient neural networks (GNN), such RNN (or termed specifically as Zhang neural networks, ZNN) models are elegantly designed by ...
Yunong Zhang, Yiwen Yang, Ning Tan 0003
openaire +2 more sources
Zhang neural network and its application to Newton iteration for matrix square root estimation
Neural Computing and Applications, 2010A special class of recurrent neural networks (RNN) has recently been proposed by Zhang et al. for solving online time-varying matrix problems. Being different from conventional gradient-based neural networks (GNN), such RNN (termed specifically as Zhang neural networks, ZNN) are designed based on matrix-valued error functions, instead of scalar-valued ...
Yunong Zhang +3 more
openaire +2 more sources
Zhang neural networks for a set of linear matrix inequalities with time-varying coefficient matrix
Information Processing Letters, 2016zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Jia Sun, Shiheng Wang, Ke Wang
openaire +2 more sources
Robustness analysis of the Zhang neural network for online time-varying quadratic optimization
Journal of Physics A: Mathematical and Theoretical, 2010A general type of recurrent neural network (termed as Zhang neural network, ZNN) has recently been proposed by Zhang et al for the online solution of time-varying quadratic-minimization (QM) and quadratic-programming (QP) problems. Global exponential convergence of the ZNN could be achieved theoretically in an ideal error-free situation. In this paper,
Yunong Zhang +3 more
openaire +2 more sources
Zhang neural network solving for time-varying full-rank matrix Moore–Penrose inverse
Computing, 2010zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Yunong Zhang +3 more
openaire +1 more source
The link between newton iteration for matrix inversion and Zhang neural network (ZNN)
2008 IEEE International Conference on Industrial Technology, 2008Different from gradient-based neural networks, a special kind of recurrent neural network has recently been proposed by Zhang et al for online matrix inversion. Such a neural network is designed based on a matrix-valued error function instead of a scalar-valued norm-based error function.
null Yunong Zhang +2 more
openaire +1 more source
2008 IEEE International Conference on Networking, Sensing and Control, 2008
Recently, a special kind of recurrent neural networks (RNN) with implicit dynamics has been proposed by Zhang et al for online time-varying problems solving (such as time-varying matrix inversion). Such a neural-dynamic system is elegantly designed by defining a matrix-valued error function rather than the usual scalar-valued norm-based error function.
Yunong Zhang +4 more
openaire +1 more source
Recently, a special kind of recurrent neural networks (RNN) with implicit dynamics has been proposed by Zhang et al for online time-varying problems solving (such as time-varying matrix inversion). Such a neural-dynamic system is elegantly designed by defining a matrix-valued error function rather than the usual scalar-valued norm-based error function.
Yunong Zhang +4 more
openaire +1 more source
Gradient-Zhang Neural Network Solving Linear Time-Varying Equations
2022 IEEE 17th Conference on Industrial Electronics and Applications (ICIEA), 2022Yunong Zhang, Changyuan Wang
openaire +1 more source
Two New Zhang Neural Networks for Solving Time-Varying Linear Equations and Inequalities Systems
IEEE Transactions on Neural Networks and Learning Systems, 2023Bing Zheng, Wenqi Wu
exaly