Back to search

University of Arkansas

Analysis and Construction of Artificial Neural Networks for the Heat Equations, and Their Associated Parameters, Depths, and Accuracies.

Abstract

dc:description.abstract

This dissertation seeks to explore a certain calculus for artificial neural networks. Specifically we will be looking at versions of the heat equation, and exploring strategies on how to approximate them. Our strategy towards the beginning will be to take a technique called Multi-Level Picard (MLP), and present a simplified version of it showing that it converges to a solution of the equation (∂/∂t ud ) (t, x) = (∇2 x ud)(t, x). We will then take a small detour exploring the viscosity super-solution properties of solutions to such equations. It is here that we will first encounter Feynman-Kac, and see that solutions to these equations can be expressed the expected value of a certain stochastic integral. The final and last part of the dissertation will be dedicated to expanding a certain neural network framework. We will build on this framework by introducing new operations, namely raising to a power, and use this to build out neural network polynomials. This opens the gateway for approximating transcendental functions such as exp (x), sin (x), and cos(x). This, coupled with a trapezoidal rule mechanism for integration allows us to approximate expressions of the form exp (∫ b a □dt ). We will, in the last chapter, look at how the technology of neural networks developed in the previous two chapters work towards approximating the expression that Feynman-Kac asserts must be the solution to these modified heat equations. We will then end by giving approximate bounds for the error in the Monte Carlo method. All the while we will maintain that the parameter estimates and depth estimates remain polynomial on 1/ε. As an added bonus we will also look at the simplified MLP technique from the previous chapters of this dissertation and show that yes, they can indeed be approximated with artificial neural networks, and that yes, they can be done so with neural networks whose parameters and depth counts grow only polynomially on 1/ε. Our appendix will contain code listings of these neural network operations, some of the architectures, and some small scale simulation results.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy in Mathematics (PhD)
Level thesis:degree_level
Dissertation
Department thesis:degree_department
Mathematical Sciences
Year dc:date.available
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Rafi, Shakil Ahmed
Advisor dc:contributor.advisor
  • Padgett, Joshua L.
Contributors dc:contributor
  • Nakarmi, Ukash
  • Chen, Jiahui

Subjects

dc:subject × 7

Identifiers

dc:identifier.*
Repository record dc:identifier
https://scholarworks.uark.edu/etd/5277

Chain of custody

source
Harvested from
University of Arkansas
Base URL
scholarworks.uark.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Rafi, Shakil Ahmed. Analysis and Construction of Artificial Neural Networks for the Heat Equations, and Their Associated Parameters, Depths, and Accuracies.. Dissertation thesis, 2024. https://scholarworks.uark.edu/etd/5277