A probabilistic approach to parallel dynamics for the Little-Hopfield model
- 21 July 1991
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 24 (14) , 3413-3426
- https://doi.org/10.1088/0305-4470/24/14/028
Abstract
Presents new results on a probabilistic approach to parallel dynamics of the Little-Hopfield model. The authors propose a truncated auxiliary dynamics method to control a feedback noise in this symmetrical neural network with full connection. It allows them to propose an ansatz for derivation of the explicit recurrence relations for the main and residual (noisy) overlap evolution for arbitrary discrete moment t.Keywords
This publication has 18 references indexed in Scilit:
- Parallel dynamic for an extremely diluted neural networkJournal of Physics A: General Physics, 1990
- Properties of sparsely connected excitatory neural networksPhysical Review A, 1990
- Dynamics of a multi-layered perceptron model : a rigorous resultJournal de Physique, 1990
- Layered neural networksJournal of Physics A: General Physics, 1989
- Chaotic behavior of a layered neural networkPhysical Review A, 1988
- Layered feed-forward neural network with exactly soluble dynamicsPhysical Review A, 1988
- An Exactly Solvable Asymmetric Neural Network ModelEurophysics Letters, 1987
- Storing and Retrieving Information in a Layered Spin SystemEurophysics Letters, 1986
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- The existence of persistent states in the brainMathematical Biosciences, 1974