Fabián Aguirre-López 1 Mauro Pastore 1 Silvio Franz 1
Fabián Aguirre-López, Mauro Pastore, Silvio Franz. Satisfiability transition in asymmetric neural networks. Journal of Physics A: Mathematical and Theoretical, IOP Publishing, 2022. ⟨hal-03721474⟩
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.
- 1. LPTMS – Laboratoire de Physique Théorique et Modèles Statistiques