Layered Dissipative Neural Fields: Bounding the Dimension of the Population Activity Manifold with Infinitely Many Neurons
Abstract
We consider a class of neural field models describing the macroscopic activity of an infinite population of neurons organized into finitely many stacked layers, written as a system of semi-linear higher-order parabolic equations. For this class of biologically inspired equations, we show that the higher-order dissipation, modeling gap junction activity regulation, induces a spectral gap ensuring that the associated semigroup possesses an inertial manifold, that is, a finite-dimensional manifold attracting all orbits of the infinite-dimensional system of neural activity. Our main result is an upper bound on the dimension of this manifold, giving its explicit scaling in the dissipation order and strength, the leaking rate, and the norm of the connection operator. We interpret this as a step toward the mathematical modeling of the empirically motivated concept of neural manifold, namely the idea that the collective activity of a large neural population lies on a low-dimensional manifold. For this class of equations, we further prove universal approximation properties, namely stationary pattern expressivity in terms of the input and input-dependent dynamical expressivity over finite time horizons. Finally, we provide sufficient conditions for the existence of traveling waves and nontrivial stationary solutions.
Related
- Bounding martingale dimension by spectral dimension
- A nilpotent quotient algorithm for certain infinitely presented groups and its applications
- Bounding the Risk Difference Bias Given Incomplete Parameters for Externally Adjusting Uncontrolled Confounding
- Characterizing variation bounding in discrete-time Hankel operators
- Identification and Bounding of Joint Expectation over Potential Outcomes
BibTeX
@misc{rakotomalala2026layered,
title = {{Layered Dissipative Neural Fields: Bounding the Dimension of the Population Activity Manifold with Infinitely Many Neurons}},
author = {Matthias Rakotomalala and Johannes Zimmer},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.18774},
eprint = {2609.18774},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.18774},
}
RIS
TY - UNPB
TI - Layered Dissipative Neural Fields: Bounding the Dimension of the Population Activity Manifold with Infinitely Many Neurons
AU - Matthias Rakotomalala
AU - Johannes Zimmer
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.18774
UR - https://arxiv.org/abs/2609.18774
AB - We consider a class of neural field models describing the macroscopic activity of an infinite population of neurons organized into finitely many stacked layers, written as a system of semi-linear higher-order parabolic equations. For this class of biologically inspired equations, we show that the higher-order dissipation, modeling gap junction activity regulation, induces a spectral gap ensuring that the associated semigroup possesses an inertial manifold, that is, a finite-dimensional manifold attracting all orbits of the infinite-dimensional system of neural activity. Our main result is an upper bound on the dimension of this manifold, giving its explicit scaling in the dissipation order and strength, the leaking rate, and the norm of the connection operator. We interpret this as a step toward the mathematical modeling of the empirically motivated concept of neural manifold, namely the idea that the collective activity of a large neural population lies on a low-dimensional manifold. For this class of equations, we further prove universal approximation properties, namely stationary pattern expressivity in terms of the input and input-dependent dynamical expressivity over finite time horizons. Finally, we provide sufficient conditions for the existence of traveling waves and nontrivial stationary solutions.
ER -