A Caltech Library Service

Stability-capacity diagram of a neural network with Ising bonds

Amaldi, E. and Nicolis, S. (1989) Stability-capacity diagram of a neural network with Ising bonds. Journal de Physique, 50 (17). pp. 2333-2345. ISSN 0302-0738. doi:10.1051/jphys:0198900500170233300.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


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 one.

Item Type:Article
Related URLs:
URLURL TypeDescription
Additional Information:© 1989 Société Française de Physique.
Subject Keywords:Ising model; neural nets; optimisation; phase diagrams; stability
Issue or Number:17
Classification Code:PACS: 0550 - Lattice theory and statistics (Ising, Potts, etc.); 0270 - Computational techniques
Record Number:CaltechAUTHORS:20200424-093442750
Persistent URL:
Official Citation:Stability-capacity diagram of a neural network with Ising bonds. E. Amaldi et S. Nicolis. J. Phys. France, 50 17 (1989) 2333-2345; DOI:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:102771
Deposited By: Tony Diaz
Deposited On:24 Apr 2020 16:43
Last Modified:16 Nov 2021 18:15

Repository Staff Only: item control page