Transient Dynamics of Sparsely Connected Hopfield Neural Networks with Arbitrary Degree Distributions
arXiv:0704.1007 · doi:10.1016/j.physa.2007.09.047
Abstract
Using probabilistic approach, the transient dynamics of sparsely connected Hopfield neural networks is studied for arbitrary degree distributions. A recursive scheme is developed to determine the time evolution of overlap parameters. As illustrative examples, the explicit calculations of dynamics for networks with binomial, power-law, and uniform degree distribution are performed. The results are good agreement with the extensive numerical simulations. It indicates that with the same average degree, there is a gradual improvement of network performance with increasing sharpness of its degree distribution, and the most efficient degree distribution for global storage of patterns is the delta function.
11 pages, 5 figures. Any comments are favored
References in corpus (10)
- Performance of networks of artificial neurons: The role of clustering
- Efficient Hopfield pattern recognition on a scale-free neural network
- Fastest learning in small world neural networks
- Topology and Computational Performance of Attractor Neural Networks
- Finite Connectivity Attractor Neural Networks
- Stability of a neural network model with small-world connections
- The Little-Hopfield model on a Random Graph
- The signal-to-noise analysis of the Little-Hopfield model revisited
- Mean-field dynamics of sequence processing neural networks with finite connectivity
- Topology and Dynamics of Attractor Neural Networks: The Role of Loopiness