The roles of stability and symmetry in the dynamics of neural networks
- 7 July 1988
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 21 (13) , 2995-3011
- https://doi.org/10.1088/0305-4470/21/13/022
Abstract
The authors study the retrieval phase of spin-glass-like neural networks. Considering that the dynamics should depend only on gauge-invariant quantities, they propose that two such parameters, characterising the symmetry of the neural net's connections and the stabilities of the patterns, are responsible for most of the dynamical effects. This is supported by a numerical study of the shape of the basins of attraction for a one-pattern neural network model. The effects of stability and symmetry on the short-time dynamics of this model are studied analytically, and the full dynamics for vanishing symmetry is shown to be exactly solvable.Keywords
This publication has 15 references indexed in Scilit:
- The nature of attractors in an asymmetric spin glass with deterministic dynamicsJournal of Physics A: General Physics, 1988
- Content-addressability and learning in neural networksJournal of Physics A: General Physics, 1988
- Maximum Storage Capacity in Neural NetworksEurophysics Letters, 1987
- Learning algorithms with optimal stability in neural networksJournal of Physics A: General Physics, 1987
- An Exactly Solvable Asymmetric Neural Network ModelEurophysics Letters, 1987
- Learning of correlated patterns in spin-glass networks by local learning rulesPhysical Review Letters, 1987
- Associative recall of memory without errorsPhysical Review A, 1987
- Zero temperature parallel dynamics for infinite range spin glasses and neural networksJournal de Physique, 1987
- Information storage and retrieval in spin-glass like neural networksJournal de Physique Lettres, 1985
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982