On the number of limit cycles in asymmetric neural networks

Abstract

The comprehension of the mechanisms at the basis of the functioning of complexly interconnected networks represents one of the main goals of neuroscience. In this work, we investigate how the structure of recurrent connectivity influences the ability of a network to have storable patterns and in particular limit cycles, by modeling a recurrent neural network with McCulloch-Pitts neurons as a content-addressable memory system. A key role in such models is played by the connectivity matrix, which, for neural networks, corresponds to a schematic representation of the "connectome": the set of chemical synapses and electrical junctions among neurons. The shape of the recurrent connectivity matrix plays a crucial role in the process of storing memories. This relation has already been exposed by the work of Tanaka and Edwards, which presents a theoretical approach to evaluate the mean number of fixed points in a fully connected model at thermodynamic limit. Interestingly, further studies on the same kind of model but with a finite number of nodes have shown how the symmetry parameter influences the types of attractors featured in the system. Our study extends the work of Tanaka and Edwards by providing a theoretical evaluation of the mean number of attractors of any given length $L$ for different degrees of symmetry in the connectivity matrices.

arXiv comment35 pages, 12 figures

References in corpus (7)

• Spin-Glass Theory for Pedestrians
• Dynamics of Random Neural Networks with Bistable Units
• Optimal sequence memory in driven random networks
• Path Integral Approach to Random Neural Networks
• Effect of dilution in asymmetric recurrent neural networks
• Relaxation, closing probabilities and transition from oscillatory to chaotic attractors in asymmetric neural networks
• Attractors in fully asymmetric neural networks

Cited by in corpus (9)

• Transient chaotic dimensionality expansion by recurrent networks
• Supervised perceptron learning vs unsupervised Hebbian unlearning: Approaching optimal memory retrieval in Hopfield-like networks
• Dynamically selected steady states and criticality in non-reciprocal networks
• On the number of limit cycles in diluted neural networks
• Unlearnable Games and "Satisficing'' Decisions: A Simple Model for a Complex World
• Quenches in the Sherrington-Kirkpatrick model
• A new spin on optimal portfolios and ecological equilibria
• Satisfiability transition in asymmetric neural networks
• Dynamical Cavity Method for Hypergraphs and its Application to Quenches in the k-XOR-SAT Problem