Qualitative behaviour of some simple networks
- 21 August 1996
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 29 (16) , 5019-5033
- https://doi.org/10.1088/0305-4470/29/16/023
Abstract
Some classical neural network systems including the Hartline - Ratliff system, the Linsker system, and the general sigmoid dynamics, are reconsidered within a more general class of dynamical systems. For synchronous dynamics the existence, uniqueness, local and global stability of stationary points is investigated. For asynchronous dynamics a convergence theorem is proved. The application of the theory of quasimonotone flows leads to some insights so far not widespread in network theory.Keywords
This publication has 15 references indexed in Scilit:
- On Neurodynamics with Limiter Function and Linsker's Developmental ModelNeural Computation, 1996
- Piecewise affine bijections of Rn, and the equation Sx+−Tx−=yLinear Algebra and its Applications, 1987
- Stationary states of the Hartline-Ratliff modelBiological Cybernetics, 1987
- From basic network principles to neural architecture: emergence of orientation columns.Proceedings of the National Academy of Sciences, 1986
- Systems of Differential Equations that are Competitive or Cooperative II: Convergence Almost EverywhereSIAM Journal on Mathematical Analysis, 1985
- Competition for fluctuating nutrientJournal of Mathematical Biology, 1983
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- Systems of Differential Equations Which Are Competitive or Cooperative: I. Limit SetsSIAM Journal on Mathematical Analysis, 1982
- The Jacobian matrix and global univalence of mappingsMathematische Annalen, 1965
- SPATIAL SUMMATION OF INHIBITORY INFLUENCES IN THE EYE OF LIMULUS, AND THE MUTUAL INTERACTION OF RECEPTOR UNITSThe Journal of general physiology, 1958