Message passing algorithms for the Hopfield network reconstruction: threshold behavior and limitation
arXiv:1009.0069 · doi:10.1103/PhysRevE.82.056111
Abstract
The Hopfield network is reconstructed as an inverse Ising problem by passing messages. The applied susceptibility propagation algorithm is shown to improve significantly on other mean-field-type methods and extends well into the low temperature region. However, this iterative algorithm is limited by the nature of the supplied data. Its performance deteriorates as the data becomes highly magnetized, and this method finally fails in the presence of the frozen type data where at least two of its magnetizations are equal to one in absolute value. On the other hand, a threshold behavior is observed for the susceptibility propagation algorithm and the transition from good reconstruction to poor one becomes sharper as the network size increases.
arXiv comment10 pages, 4 figures, appendixes and references added
References in corpus (16)
- Weak pairwise correlations imply strongly correlated network states in a neural population
- Identification of direct residue contacts in protein-protein interaction by message passing
- Maximum entropy models for antibody diversity
- The Ising Model for Neural Data: Model Quality and Approximate Methods for Extracting Functional Connectivity
- Glass models on Bethe lattices
- Learning by message-passing in networks of discrete synapses
- Statistical physics of pairwise probability models
- Small-correlation expansions for the inverse Ising problem
- Finite Connectivity Attractor Neural Networks
- Locked constraint satisfaction problems
- The Little-Hopfield model on a Random Graph
- Intrinsic limitations of inverse inference in the pairwise Ising spin glass
- Reconstructing the Hopfield network as an inverse Ising problem
- Cavity approach to the Sourlas code system
- Survey propagation at finite temperature: application to a Sourlas code as a toy model
- Susceptibility Propagation for Constraint Satisfaction Problems