Asymmetric neural networks with multispin interactions
- 1 December 1988
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review A
- Vol. 38 (11) , 5972-5975
- https://doi.org/10.1103/physreva.38.5972
Abstract
A dilute nonsymmetric ferromagnetic neural network with multispin interactions and a version of the Hopfield model with multispin interactions are solved in the limit where the average number of inputs per spin is finite. It is found that in such asymmetric systems the critical exponents of local quantities can take a few different values, instead of just one.Keywords
This publication has 10 references indexed in Scilit:
- Inhomogeneous Magnetization in Dilute Asymmetric and Symmetric SystemsPhysical Review Letters, 1988
- Potts-glass models of neural networksPhysical Review A, 1988
- An Exactly Solvable Asymmetric Neural Network ModelEurophysics Letters, 1987
- Random Networks of Automata: A Simple Annealed ApproximationEurophysics Letters, 1986
- Evolution of overlaps between configurations in random Boolean networksJournal de Physique, 1986
- Storing Infinite Numbers of Patterns in a Spin-Glass Model of Neural NetworksPhysical Review Letters, 1985
- Spin-glass models of neural networksPhysical Review A, 1985
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- The existence of persistent states in the brainMathematical Biosciences, 1974