Stability-capacity diagram of a neural network with Ising bonds
- 1 January 1989
- journal article
- Published by EDP Sciences in Journal de Physique
- Vol. 50 (17) , 2333-2345
- https://doi.org/10.1051/jphys:0198900500170233300
Abstract
The stability-capacity diagram of a fully connected neural network, whose bonds take the values 1 and -1 with equal probability, is determined numerically. Two different optimization methods (simulated annealing and tabu search) are used and their relevant features are discussed. The results indicate the existence of a region, in the stability-capacity plane, where replica-symmetry should be broken, within the replica-symmetric phase found by previous, analytical, computations. The critical capacity, consistent with simple arguments on information storage, is found to be less than oneKeywords
This publication has 7 references indexed in Scilit:
- Optimal storage properties of neural network modelsJournal of Physics A: General Physics, 1988
- The space of interactions in neural network modelsJournal of Physics A: General Physics, 1988
- Using tabu search techniques for graph coloringComputing, 1987
- Learning algorithms with optimal stability in neural networksJournal of Physics A: General Physics, 1987
- Information storage in neural networks with low levels of activityPhysical Review A, 1987
- Interactive decision software and computer graphics for architectural and space planningAnnals of Operations Research, 1985
- Optimization by Simulated AnnealingScience, 1983