Coupled dynamics of fast spins and slow interactions in neural networks and spin systems
- 7 August 1993
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 26 (15) , 3681-3695
- https://doi.org/10.1088/0305-4470/26/15/018
Abstract
The authors examine an Ising spin system in which both spins and the interactions between them may evolve in time, although on disparate timescales, such that the couplings change adiabatically. In thermal equilibrium they find a novel application of the replica method, but for finite replica number, representing the ratio of the temperatures of the spin and interaction systems. Regimes where the motion of the couplings has non-trivial effects are found in addition to those where solely the stochasticity of these interaction weights in significant, and this issue is closely related to the orders of the transitions between the various phases observed. Simulation results lend support to the analysis.Keywords
This publication has 15 references indexed in Scilit:
- Statistical mechanics of neural networks near saturationPublished by Elsevier ,2004
- Unsupervised dynamic learning in layered neural networksJournal of Physics A: General Physics, 1991
- Storage capacity of memory networks with binary couplingsJournal de Physique, 1989
- Image evolution in Hopfield networksPhysical Review A, 1988
- The space of interactions in neural network modelsJournal of Physics A: General Physics, 1988
- Parisi's mean-field solution for spin glasses as an analytic continuation in the replica numberJournal of Physics A: General Physics, 1983
- Eigenvalues of the stability matrix for Parisi solution of the long-range spin-glassPhysical Review B, 1983
- The order parameter for spin glasses: a function on the interval 0-1Journal of Physics A: General Physics, 1980
- Infinite-ranged models of spin-glassesPhysical Review B, 1978
- Stability of the Sherrington-Kirkpatrick solution of a spin glass modelJournal of Physics A: General Physics, 1978