Stability properties of Potts neural networks with biased patterns and low loading
- 7 March 1991
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 24 (5) , 1065-1081
- https://doi.org/10.1088/0305-4470/24/5/021
Abstract
The q-state Potts glass model of neural networks is extended to include biased patterns. For a finite number of such patterns, the existence and stability properties of the Mattis states and symmetric states are discussed in detail as a function of the bias. Analytic results are presented for all q at zero temperature. For finite temperatures numerical results are obtained for q=3 and two classes of representative bias parameters. A comparison is made with the Hopfield model.Keywords
This publication has 12 references indexed in Scilit:
- Two-state representations of three-state neural networksJournal of Physics A: General Physics, 1990
- The mean-field theory of a Q-state neural network modelJournal of Physics A: General Physics, 1989
- Neural networks that use three-state neuronsJournal of Physics A: General Physics, 1989
- Information processing in three-state neural networksJournal of Statistical Physics, 1989
- Discrete-state phasor neural networksPhysical Review A, 1988
- Potts-glass models of neural networksPhysical Review A, 1988
- The equivalence between discrete-spin Hamiltonians and Ising Hamiltonians with multi-spin interactionsJournal of Physics C: Solid State Physics, 1987
- Information storage in neural networks with low levels of activityPhysical Review A, 1987
- The infinite-range clock spin glass model: an investigation of the relevance of reflection symmetryJournal of Physics C: Solid State Physics, 1986
- Spin glass, ferromagnetic and mixed phases in the disordered Potts modelJournal of Physics C: Solid State Physics, 1983