Recurrent Neural Networks for Computing Pseudoinverses of Rank-Deficient Matrices

From MaRDI portal
Publication:4376230


DOI10.1137/S1064827594267161zbMath0891.93034MaRDI QIDQ4376230

Jun Wang

Publication date: 10 February 1998

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/s1064827594267161


68T05: Learning and adaptive systems in artificial intelligence

90C20: Quadratic programming

15A09: Theory of matrix inversion and generalized inverses

93C05: Linear systems in control theory


Related Items

Complex ZNN for computing time-varying weighted pseudo-inverses, A noise-tolerant fast convergence ZNN for dynamic matrix inversion, A Novel Iterative Method for Computing Generalized Inverse, Recurrent Neural Network Approach Based on the Integral Representation of the Drazin Inverse, Recurrent Neural Network for Computing Outer Inverse, Complex Neural Network Models for Time-Varying Drazin Inverse, Recurrent neural networks for computing weighted Moore-Penrose inverse, Recurrent neural networks for nonlinear output regulation, Varying-parameter Zhang neural network for approximating some expressions involving outer inverses, Neural network approach to computing outer inverses based on the full rank representation, Zhang neural network solving for time-varying full-rank matrix Moore-Penrose inverse, Neural network for computing pseudoinverses and outer inverses of complex-valued matrices, Exponential stability of hybrid stochastic recurrent neural networks with time-varying delays, Complex recurrent neural network for computing the inverse and pseudo-inverse of the complex matrix, Augmented gradient flows for on-line robust pole assignment via state and output feedback, Conditions for existence, representations, and computation of matrix generalized inverses, Recurrent neural network for computing the \(W\)-weighted Drazin inverse, Discrete-time noise-tolerant Zhang neural network for dynamic matrix pseudoinversion, Two finite-time convergent Zhang neural network models for time-varying complex matrix Drazin inverse, From Penrose equations to Zhang neural network, Getz-Marsden dynamic system, and DDD (direct derivative dynamics) using substitution technique, General 9-instant discrete-time Zhang neural network for time-dependent applications, Properties and computation of continuous-time solutions to linear systems, Exact solutions and convergence of gradient based dynamical systems for computing outer inverses, A recurrent neural network computing the largest imaginary or real part of eigenvalues of real matrices, IMPROVED SUFFICIENT CONDITIONS FOR GLOBAL EXPONENTIAL STABILITY OF RECURRENT NEURAL NETWORKS WITH DISTRIBUTED DELAYS