Parallel dynamics of the neural network with the pseudoinverse coupling matrix
- 1 May 1991
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 24 (9), 2201-2218
- https://doi.org/10.1088/0305-4470/24/9/026
Abstract
The authors investigate the parallel dynamics of the neural network with the pseudoinverse coupling matrix. Based on an exact dynamic theory they develop an approximate treatment for long timescales. The temporal development of the overlap, of correlation functions and of the remanent magnetization are investigated. They present results for deterministic and stochastic dynamics. Large-scale numerical simulations supplement their analytical findings.Keywords
This publication has 22 references indexed in Scilit:
- Layered neural networksJournal of Physics A: General Physics, 1989
- Learning in Neural Networks: Solvable DynamicsEurophysics Letters, 1989
- An Exactly Solvable Asymmetric Neural Network ModelEurophysics Letters, 1987
- Learning of correlated patterns in spin-glass networks by local learning rulesPhysical Review Letters, 1987
- Associative recall of memory without errorsPhysical Review A, 1987
- Collective computational properties of neural networks: New learning mechanismsPhysical Review A, 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
- Analytic study of the memory storage capacity of a neural networkMathematical Biosciences, 1978
- The existence of persistent states in the brainMathematical Biosciences, 1974