The dual of the space of interactions in neural network models
arXiv:1505.02963 · doi:10.1142/S0129183116500674
Abstract
In this work the Gardner problem of inferring interactions and fields for an Ising neural network from given patterns under a local stability hypothesis is addressed under a dual perspective. By means of duality arguments an integer linear system is defined whose solution space is the dual of the Gardner space and whose solutions represent mutually unstable patterns. We propose and discuss Monte Carlo methods in order to find and remove unstable patterns and uniformly sample the space of interactions thereafter. We illustrate the problem on a set of real data and perform ensemble calculation that shows how the emergence of phase dominated by unstable patterns can be triggered in a non-linear discontinuous way.
arXiv comment13 pages, 4 figures, 1 table
References in corpus (9)
- Weak pairwise correlations imply strongly correlated network states in a neural population
- Searching for collective behavior in a network of real neurons
- The Bethe approximation for solving the inverse Ising problem: a comparison with other inference methods
- On sampling and modeling complex systems
- On the criticality of inferred models
- Counting and correcting thermodynamically infeasible flux cycles in genome-scale metabolic networks
- How glassy are neural networks?
- Hierarchical neural networks perform both serial and parallel processing
- A weighted belief-propagation algorithm to estimate volume-related properties of random polytopes