Robustness Analyses and Optimal Sampling Gap of Recurrent Neural Network for Dynamic Matrix Pseudoinversion
- 20 September 2017
- journal article
- Published by Fuji Technology Press Ltd. in Journal of Advanced Computational Intelligence and Intelligent Informatics
- Vol. 21 (5), 778-784
- https://doi.org/10.20965/jaciii.2017.p0778
Abstract
This study analyses the robustness and convergence characteristics of a neural network. First, a special class of recurrent neural network (RNN), termed a continuous-time Zhang neural network (CTZNN) model, is presented and investigated for dynamic matrix pseudoinversion. Theoretical analysis of the CTZNN model demonstrates that it has good robustness against various types of noise. In addition, considering the requirements of digital implementation and online computation, the optimal sampling gap for a discrete-time Zhang neural network (DTZNN) model under noisy environments is proposed. Finally, experimental results are presented, which further substantiate the theoretical analyses and demonstrate the effectiveness of the proposed ZNN models for computing a dynamic matrix pseudoinverse under noisy environments.Keywords
This publication has 19 references indexed in Scilit:
- Novel Complex-Valued Neural Network for Dynamic Complex-Valued Matrix InversionJournal of Advanced Computational Intelligence and Intelligent Informatics, 2016
- A class of finite-time dual neural networks for solving quadratic programming problems and its k-winners-take-all applicationNeural Networks, 2013
- Iterative method for computing the Moore–Penrose inverse based on Penrose equationsJournal of Computational and Applied Mathematics, 2011
- Digital Image Reconstruction in the Spectral Domain Utilizing the Moore-Penrose InverseMathematical Problems in Engineering, 2010
- Method of elementary transformation to compute Moore–Penrose inverseApplied Mathematics and Computation, 2010
- Pseudo-inverse Jacobian control with grey relational analysis for robot manipulators mounted on oscillatory basesJournal of Sound and Vibration, 2009
- Symbolic computation of weighted Moore–Penrose inverse using partitioning methodApplied Mathematics and Computation, 2007
- An improved Newton iteration for the weighted Moore–Penrose inverseApplied Mathematics and Computation, 2006
- Face Recognition by Applying Wavelet Subband Representation and Kernel Associative MemoryIEEE Transactions on Neural Networks, 2004
- A subspace approach to blind space-time signal processing for wireless communication systemsIEEE Transactions on Signal Processing, 1997