Optimal capacity of the Blume-Emery-Griffiths perceptron
- 21 March 2003
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 67 (3) , 036113
Abstract
A Blume-Emery-Griffiths perceptron model is introduced and its optimal capacity is calculated within the replica-symmetric Gardner approach, as a function of the pattern activity and the embedding stability parameter. The stability of the replica-symmetric approximation is studied via the analog of the de Almeida–Thouless line. A comparison is made with other three-state perceptrons.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Parallel dynamics of the fully connected Blume–Emery–Griffiths neural networkPhysica A: Statistical Mechanics and its Applications, 2003
- An optimal Q-state neural network using mutual informationPhysics Letters A, 2002
- Three-state neural network: From mutual information to the HamiltonianPhysical Review E, 2000
- Effects of random biquadratic couplings in a spin-1 spin-glass modelThe European Physical Journal B, 2000
- Storage capacity and optimal learning of Potts-model perceptrons by a cavity methodJournal of Physics A: General Physics, 1994
- Learning grey-toned patterns in neural networksJournal of Physics A: General Physics, 1991
- Neural networks with many-neuron interactionsJournal de Physique, 1990
- Ising Model for theTransition and Phase Separation in-MixturesPhysical Review A, 1971
- On the possibility of first-order phase transitions in Ising systems of triplet ions with zero-field splittingPhysica, 1966
- Theory of the First-Order Magnetic Phase Change in UPhysical Review B, 1966