Satisfiability transition in asymmetric neural networks

Abstract

Asymmetry in the synaptic interactions between neurons plays a crucial role in determining the memory storage and retrieval properties of recurrent neural networks. In this work, we analyze the problem of storing random memories in a network of neurons connected by a synaptic matrix with a definite degree of asymmetry. We study the corresponding satisfiability and clustering transitions in the space of solutions of the constraint satisfaction problem associated with finding synaptic matrices given the memories. We find, besides the usual SAT/UNSAT transition at a critical number of memories to store in the network, an additional transition for very asymmetric matrices, where the competing constraints (definite asymmetry vs. memories storage) induce enough frustration in the problem to make it impossible to solve. This finding is particularly striking in the case of a single memory to store, where no quenched disorder is present in the system.

arXiv comment24 pages + appendix, 7 figures

References in corpus (22)

• Stability Criteria for Complex Ecosystems
• Non-reciprocal phase transitions
• Gibbs States and the Set of Solutions of Random Constraint Satisfaction Problems
• Crises and collective socio-economic phenomena: simple models and challenges
• Spectra of Sparse Random Matrices
• Universality of the SAT-UNSAT (jamming) threshold in non-convex continuous constraint satisfaction problems
• Numerical implementation of dynamical mean field theory for disordered systems: application to the Lotka-Volterra model of ecosystems
• Properties of equilibria and glassy phases of the random Lotka-Volterra model with demographic noise
• Dynamically evolved community size and stability of random Lotka-Volterra ecosystems
• May's Instability in Large Economies
• Jamming in multilayer supervised learning models
• Replica Fourier Transforms on Ultrametric Trees, and Block-Diagonalizing Multi-Replica Matrices
• Random replicators with asymmetric couplings
• Transition from regular to complex behaviour in a discrete deterministic asymmetric neural network model
• Effect of dilution in asymmetric recurrent neural networks
• Statistical learning theory of structured data
• Supervised perceptron learning vs unsupervised Hebbian unlearning: Approaching optimal memory retrieval in Hopfield-like networks
• Counting equilibria in a random non-gradient dynamics with heterogeneous relaxation rates
• On the number of limit cycles in asymmetric neural networks
• Beyond the storage capacity: data driven satisfiability transition
• On the number of limit cycles in diluted neural networks
• Imaginary replica analysis of loopy regular random graphs

Cited by in corpus (1)

• Supervised perceptron learning vs unsupervised Hebbian unlearning: Approaching optimal memory retrieval in Hopfield-like networks