Symmetry breaking in nonmonotonic neural networks
- 21 June 1993
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 26 (12) , L507-L513
- https://doi.org/10.1088/0305-4470/26/12/005
Abstract
The optimal performance of a nonmonotonic neural network is studied by the replica method. In analogy to what happens in multi-layered networks, the authors show that replica symmetry breaking (RSB) is required. The distribution of the patterns stabilities, the correlations in the distribution of the internal representation and the optimal capacity per synapse ( alpha c approximately=4.8) are computed with one step of RSB.Keywords
This publication has 6 references indexed in Scilit:
- A real-time neural system for color constancyIEEE Transactions on Neural Networks, 1991
- Statistical mechanics of a multilayered neural networkPhysical Review Letters, 1990
- 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
- Domains of attraction in neural networksJournal de Physique, 1988
- Stability of the Sherrington-Kirkpatrick solution of a spin glass modelJournal of Physics A: General Physics, 1978