Stability conditions for nonlinear continuous neural networks with asymmetric connection weights

Neural Networks

Volumn 5, Issue 3, 1992, Pages 495-500

  Matsuoka, Kiyotoshi ^a  

^a KYUSHU INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Absolute stability; Asymmetric connection; Eigenvalue; Lyapunov function; Matrix measure; Matrix norm; Recurrent network; Stability condition

Indexed keywords

NEURAL NETWORKS - MATHEMATICAL MODELS;

ABSOLUTE STABILITY; ASYMMETRIC CONNECTION; LYAPUNOV FUNCTION; MATRIX MEASURE; MATRIX NORM; RECURRENT NETWORK;

NEURAL NETWORKS;

EID: 0026679036     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(92)90011-7     Document Type: Article

References (16)

1. A learning rule for asynchronous perceptrons with feedback in a combinatorial environment
2. Backpropagation in non-feedforward networks
3. Learning on a general network
4. Adjoint-operator algorithms for learning in neural networks
5. Absolute stability of global pattern information and parallel memory storage by competitive neural networks
6. On the stability, storage capacity, and design of nonlinear continuous neural networks
7. Convergent activation dynamics in continuous time networks
8. Neurons with graded response have collective computational properties like those of two-state neurons
9. Stability in contractive nonlinear neural networks
10. On absolute stability of neural networks
11. Stability results for neural networks
12. Fixed point analysis for recurrent networks
13. Generalization of backpropagation to recurrent and higher order neural networks
14. Learning internal representations by error propagation
15. On the stability of equilibrium states of analogue neural networks