Neural networks with many-neuron interactions
- 1 January 1990
- journal article
- Published by EDP Sciences in Journal de Physique
- Vol. 51 (2) , 145-155
- https://doi.org/10.1051/jphys:01990005102014500
Abstract
The static and dynamical properties of neural networks having many-neuron interactions are studied analytically and numerically. The storage capacity of such networks is found to be unchanged from that of the more widely studied case of two-neuron interactions implying that these networks store information no more efficiently. The size of the basins of attraction in the many-neuron case is calculated exactly from a solution of the network dynamics at full connectivity and reveals that networks with many-neuron interactions are better at pattern discrimination than the simpler networks with only two-neuron interactionsKeywords
This publication has 10 references indexed in Scilit:
- Dynamical Interference between the Attractors in a Neural NetworkEurophysics Letters, 1989
- Stability-capacity diagram of a neural network with Ising bondsJournal de Physique, 1989
- Vectorized multi-site coding for nearest-neighbour neural networksJournal de Physique, 1989
- Domains of attraction in neural networksJournal de Physique, 1988
- Maximum Storage Capacity in Neural NetworksEurophysics Letters, 1987
- Exact solution of a layered neural network modelPhysical Review Letters, 1987
- Number of stable points for spin-glasses and neural networks of higher ordersPhysical Review Letters, 1987
- Associative recall of memory without errorsPhysical Review A, 1987
- Zero temperature parallel dynamics for infinite range spin glasses and neural networksJournal de Physique, 1987
- Scaling laws for the attractors of Hopfield networksJournal de Physique Lettres, 1985