Solution of a large nonlinear recurrent neural network at fixed connectivity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Wakhloo, Albert J.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918469609455616
author Wakhloo, Albert J.
author_facet Wakhloo, Albert J.
contents We calculate the moments and response functions of a nonlinear random recurrent neural network in the large $N$ limit. Our approach does not require averaging over synaptic weights and gives the first nontrivial term in a $1/\sqrt{N}$ expansion of general intensive-order correlation functions, proving a recent conjecture by Shen and Hu as a special case. Our results provide an analytical link between synaptic connectivity, correlations in spontaneous activity, and the response of a network to small perturbations.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24141
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Solution of a large nonlinear recurrent neural network at fixed connectivity
Wakhloo, Albert J.
Disordered Systems and Neural Networks
Neurons and Cognition
We calculate the moments and response functions of a nonlinear random recurrent neural network in the large $N$ limit. Our approach does not require averaging over synaptic weights and gives the first nontrivial term in a $1/\sqrt{N}$ expansion of general intensive-order correlation functions, proving a recent conjecture by Shen and Hu as a special case. Our results provide an analytical link between synaptic connectivity, correlations in spontaneous activity, and the response of a network to small perturbations.
title Solution of a large nonlinear recurrent neural network at fixed connectivity
topic Disordered Systems and Neural Networks
Neurons and Cognition
url https://arxiv.org/abs/2604.24141