Attractors in fully asymmetric neural networks
arXiv:cond-mat/9708215 · doi:10.1088/0305-4470/30/16/007
Abstract
The statistical properties of the length of the cycles and of the weights of the attraction basins in fully asymmetric neural networks (i.e. with completely uncorrelated synapses) are computed in the framework of the annealed approximation which we previously introduced for the study of Kauffman networks. Our results show that this model behaves essentially as a Random Map possessing a reversal symmetry. Comparison with numerical results suggests that the approximation could become exact in the infinite size limit.
23 pages, 6 figures, Latex, to appear on J. Phys. A
Cited by in corpus (6)
- Multiperiodic orbits from interacting soft spots in cyclically-sheared amorphous solids
- Relaxation, closing probabilities and transition from oscillatory to chaotic attractors in asymmetric neural networks
- On the number of limit cycles in asymmetric neural networks
- On the number of limit cycles in diluted neural networks
- Structure of attractors in randomly connected networks
- Probing the basins of attraction of a recurrent neural network