Back to search

University of British Columbia

Neural networks through the lens of partial differential equations : from discrete layers to continuous dynamics

Abstract

dc:description

This thesis studies deep neural networks through the lens of partial differential equations (PDEs), showing how continuous-time and operator-based perspectives can improve the stability, interpretability, and scalability of modern learning systems. Rather than treating neural networks as purely discrete stacks of layers, this work views them as discretizations of underlying dynamical systems, enabling architectural and algorithmic design guided by physical principles. We first develop the Reaction–Diffusion Neural Network (RDNN), an IMEX architecture in which each layer combines an implicit diffusion step with an explicit reaction update. This construction yields unconditional stability, helping mitigate exploding and vanishing gradients, while also improving robustness to noise and domain shifts. It further provides an interpretable framework in which learned parameters correspond to physically meaningful quantities such as diffusion and reaction coefficients. We then extend this idea by introducing the Advection–Diffusion–Reaction Neural Network (ADRNN), which incorporates a learnable transport mechanism to capture directional and long-range interactions. By combining advection, diffusion, and reaction within each layer, the resulting architecture unifies transport, smoothing, and nonlinear feature transformation in a single framework. Empirical results show that this approach improves stability and produces sharper long-horizon forecasts in spatio-temporal prediction tasks. Finally, we address the challenge of efficient training at high resolution through a multiscale optimization framework inspired by multigrid methods. To overcome the unstable gradient behavior of standard convolutions under mesh refinement, we introduce Mesh-Free Convolutions (MFCs), a class of operators derived from differential operator theory whose behavior remains stable across discretizations. Coupled with a coarse-to-fine training strategy, this framework substantially reduces computational cost while maintaining or improving predictive accuracy. Overall, this thesis demonstrates that PDE-based structure can serve not only as a tool for interpreting neural networks, but also as a principled foundation for designing models and training methods that are more stable, physically grounded, and computationally efficient.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy - PhD
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Geophysics
Grantor dc:publisher
University of British Columbia
Year dc:date
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zakariaei, Niloufar
Contributors dc:contributor
  • Haber, Eldad

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/93919

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Zakariaei, Niloufar. Neural networks through the lens of partial differential equations : from discrete layers to continuous dynamics. doctoral thesis, University of British Columbia, 2026. http://hdl.handle.net/2429/93919