State sampling dependence of the Hopfield network inference
arXiv:1104.4931 · doi:10.1088/0253-6102/57/1/27
Abstract
The fully connected Hopfield network is inferred based on observed magnetizations and pairwise correlations. We present the system in the glassy phase with low temperature and high memory load. We find that the inference error is very sensitive to the form of state sampling. When a single state is sampled to compute magnetizations and correlations, the inference error is almost indistinguishable irrespective of the sampled state. However, the error can be greatly reduced if the data is collected with state transitions. Our result holds for different disorder samples and accounts for the previously observed large fluctuations of inference error at low temperatures.
arXiv comment4 pages, 1 figure, further discussions added and relevant references added
References in corpus (9)
- Weak pairwise correlations imply strongly correlated network states in a neural population
- Are biological systems poised at criticality?
- Intrinsic limitations of inverse inference in the pairwise Ising spin glass
- Dynamics and Performance of Susceptibility Propagation on Synthetic Data
- Reconstructing the Hopfield network as an inverse Ising problem
- Out of Equilibrium Dynamics of the Hopfield Model in its spin-glass phase
- Message passing algorithms for the Hopfield network reconstruction: threshold behavior and limitation
- Large random correlations in individual mean field spin glass samples
- Distribution of equilibrium free energies in a thermodynamic system with broken ergodicity