Topology and Dynamics of Attractor Neural Networks: The Role of Loopiness
arXiv:cond-mat/0703405 · doi:10.1016/j.physa.2008.02.073
Abstract
We derive an exact representation of the topological effect on the dynamics of sequence processing neural networks within signal-to-noise analysis. A new network structure parameter, loopiness coefficient, is introduced to quantitatively study the loop effect on network dynamics. The large loopiness coefficient means the large probability of finding loops in the networks. We develop the recursive equations for the overlap parameters of neural networks in the term of the loopiness. It was found that the large loopiness increases the correlations among the network states at different times, and eventually it reduces the performance of neural networks. The theory is applied to several network topological structures, including fully-connected, densely-connected random, densely-connected regular, and densely-connected small-world, where encouraging results are obtained.
arXiv comment6 pages, 4 figures, comments are favored
References in corpus (12)
- Emergence of scaling in random networks
- Mean-field theory for scale-free random networks
- Performance of networks of artificial neurons: The role of clustering
- Efficient Hopfield pattern recognition on a scale-free neural network
- Associative memory on a small-world neural network
- Topology and Computational Performance of Attractor Neural Networks
- Finite Connectivity Attractor Neural Networks
- Phase Diagram and Storage Capacity of Sequence Processing Neural Networks
- Transient dynamics for sequence processing neural networks
- Retrieval dynamics of neural networks for sparsely coded sequential patterns
- Mean-field dynamics of sequence processing neural networks with finite connectivity
- Transient Dynamics of Sparsely Connected Hopfield Neural Networks with Arbitrary Degree Distributions