Path Integral Approach to Random Neural Networks

Abstract

In this work we study of the dynamics of large size random neural networks. Different methods have been developed to analyse their behavior, most of them rely on heuristic methods based on Gaussian assumptions regarding the fluctuations in the limit of infinite sizes. These approaches, however, do not justify the underlying assumptions systematically. Furthermore, they are incapable of deriving in general the stability of the derived mean field equations, and they are not amenable to analysis of finite size corrections. Here we present a systematic method based on Path Integrals which overcomes these limitations. We apply the method to a large non-linear rate based neural network with random asymmetric connectivity matrix. We derive the Dynamic Mean Field (DMF) equations for the system, and derive the Lyapunov exponent of the system. Although the main results are well known, here for the first time, we calculate the spectrum of fluctuations around the mean field equations from which we derive the general stability conditions for the DMF states. The methods presented here, can be applied to neural networks with more complex dynamics and architectures. In addition, the theory can be used to compute systematic finite size corrections to the mean field equations.

20 pages, 5 figures

References in corpus (2)

• Transition to chaos in random networks with cell-type-specific connectivity
• Dynamics of Random Neural Networks with Bistable Units

Cited by in corpus (37)

• Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation
• Two types of criticality in the brain
• Edge of chaos and avalanches in neural networks with heavy-tailed synaptic weight distribution
• How single neuron properties shape chaotic dynamics and signal transmission in random neural networks
• Dimension of activity in random neural networks
• Does the brain behave like a (complex) network? I. Dynamics
• The effective noise of Stochastic Gradient Descent
• Transient chaotic dimensionality expansion by recurrent networks
• Nonequilibrium thermodynamics of the asymmetric Sherrington-Kirkpatrick model
• Unified field theoretical approach to deep and recurrent neuronal networks
• Predictive coding in balanced neural networks with noise, chaos and delays
• On the number of limit cycles in asymmetric neural networks
• Large Deviations Approach to Random Recurrent Neuronal Networks: Parameter Inference and Fluctuation-Induced Transitions
• Lattice physics approaches for neural networks
• Dynamical Mean-Field Theory of Complex Systems on Sparse Directed Networks
• Self-consistent formulations for stochastic nonlinear neuronal dynamics
• Introduction to dynamical mean-field theory of randomly connected neural networks with bidirectionally correlated couplings
• Nature of the Volcano Transition in the Fully Disordered Kuramoto Model
• A Microscopic Theory of Intrinsic Timescales in Spiking Neural Networks
• Incorporating Heterogeneous Interactions for Ecological Biodiversity
• Decomposing neural networks as mappings of correlation functions
• 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
• Dynamical Theory for Adaptive Systems
• Space of Functions Computed by Deep-Layered Machines
• Effect of Synaptic Heterogeneity on Neuronal Coordination
• Role of Coupling Asymmetry in the Fully Disordered Kuramoto Model
• Counting equilibria of large complex systems by instability index
• Discontinuous transition to chaos in a canonical random neural network
• Irreversibility in Non-reciprocal Chaotic Systems
• Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model
• The meanfield limit of a network of Hopfield neurons with correlated synaptic weights
• Entropy production and irreversibility in the linearized stochastic Amari neural model
• Statistical Field Theory and Networks of Spiking Neurons
• Universality of the mean-field equations of networks of Hopfield-like neurons
• Zero-temperature dynamics of the spherical model with non-reciprocal interactions