A neural network for computing eigenvectors and eigenvalues

DOI10.1007/BF00206218zbMath0793.68123MaRDI QIDQ1182327

R. L. Waterland, Nikola Samardzija

Publication date: 28 June 1992

Published in: Biological Cybernetics (Search for Journal in Brave)

zbMATH Keywords

dynamic methodcontinuous time neural network

Mathematics Subject Classification ID

Numerical computation of eigenvalues and eigenvectors of matrices (65F15) Learning and adaptive systems in artificial intelligence (68T05) Information storage and retrieval of data (68P20) Numerical algorithms for specific classes of architectures (65Y10)

Related Items (13)

Generalized neural networks for spectral analysis: dynamics and Liapunov functions ⋮ A recurrent neural network for computing pseudoinverse matrices ⋮ A concise functional neural network computing the largest modulus eigenvalues and their corresponding eigenvectors of a real skew matrix ⋮ Real-time computation of the eigenvectors of a class of positive definite matrices ⋮ Real-time computation of singular vectors ⋮ Tensor logarithmic norm and its applications ⋮ A deep learning method for computing eigenvalues of the fractional Schrödinger operator ⋮ A recurrent neural network computing the largest imaginary or real part of eigenvalues of real matrices ⋮ Neural networks for computing eigenvalues and eigenvectors ⋮ A functional neural network computing some eigenvalues and eigenvectors of a special real matrix ⋮ Recurrent neural networks for solving linear matrix equations ⋮ Analog approach for the eigen-decomposition of positive definite matrices ⋮ Recurrent neural networks for LU decomposition and Cholesky factorization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Information storage matrices in neural networks
• Nonlinear oscillations, dynamical systems, and bifurcations of vector fields
• A theorem on non-associative algebras and its application to differential equations
• Controllability, pole placement, and stabilizability for homogenous polynomial systems
• Neural networks and physical systems with emergent collective computational abilities.
• Neurons with graded response have collective computational properties like those of two-state neurons.

This page was built for publication: A neural network for computing eigenvectors and eigenvalues