Vectorized multi-site coding for nearest-neighbour neural networks
- 1 January 1989
- journal article
- Published by EDP Sciences in Journal de Physique
- Vol. 50 (15) , 2003-2017
- https://doi.org/10.1051/jphys:0198900500150200300
Abstract
Ising spin neural networks with clipped synapses (± 1 only) and with local connectivity are simulated using multi-site coding algorithms. Speeds of over 200 neuron updates per microsecond are achieved by vectorization of the algorithm on the Cray-XMP. Results are presented for two-dimensional networks of up to 512 x 512 neurons. The networks are shown to function as associative memories and the amount of information stored compared to the amount used to store it improves upon fully-connected modelsKeywords
This publication has 8 references indexed in Scilit:
- Domains of attraction in neural networksJournal de Physique, 1988
- Maximum Storage Capacity in Neural NetworksEurophysics Letters, 1987
- Learning of correlated patterns in spin-glass networks by local learning rulesPhysical Review Letters, 1987
- Fast algorithm for the simulation of Ising modelsJournal of Statistical Physics, 1986
- Storing Infinite Numbers of Patterns in a Spin-Glass Model of Neural NetworksPhysical Review Letters, 1985
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- Tests of the multi-spin-coding technique in Monte Carlo simulations of statistical systemsComputer Physics Communications, 1981
- The existence of persistent states in the brainMathematical Biosciences, 1974