Recurrent Neural Networks for Computing Pseudoinverses of Rank-Deficient Matrices
- 1 September 1997
- journal article
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Scientific Computing
- Vol. 18 (5), 1479-1493
- https://doi.org/10.1137/s1064827594267161
Abstract
Three recurrent neural networks are presented for computing the pseudoinverses of rank-deficient matrices. The first recurrent neural network has the dynamical equation similar to the one proposed earlier for matrix inversion and is capable of Moore--Penrose inversion under the condition of zero initial states. The second recurrent neural network consists of an array of neurons corresponding to a pseudoinverse matrix with decaying self-connections and constant connections in each row or column. The third recurrent neural network consists of two layers of neuron arrays corresponding, respectively, to a pseudoinverse matrix and a Lagrangian matrix with constant connections. All three recurrent neural networks are also composed of a number of independent subnetworks corresponding to the rows or columns of a pseudoinverse. The proposed recurrent neural networks are shown to be capable of computing the pseudoinverses of rank-deficient matrices.Keywords
This publication has 17 references indexed in Scilit:
- Minimal properties of Moore-Penrose inversesLinear Algebra and its Applications, 1994
- Neural networks for computing eigenvalues and eigenvectorsBiological Cybernetics, 1992
- Neural network approach to computing matrix inversionApplied Mathematics and Computation, 1992
- Neural networks for solving systems of linear equations and related problemsIEEE Transactions on Circuits and Systems I: Regular Papers, 1992
- Electronic realisation of recurrent neural network for solving simultaneous linear equationsElectronics Letters, 1992
- Recurrent neural networks for solving systems of complex-valued linear equationsElectronics Letters, 1992
- Neural network for singular value decompositionElectronics Letters, 1992
- A neural network for computing eigenvectors and eigenvaluesBiological Cybernetics, 1991
- Dynamical systems that sort lists, diagonalize matrices, and solve linear programming problemsLinear Algebra and its Applications, 1991
- A generalized inverse for matricesMathematical Proceedings of the Cambridge Philosophical Society, 1955