Back to search

Duquesne

Mathematical Models Yield Insights into CNNs: Applications in Natural Image Restoration and Population Genetics

Abstract

dc:description.abstract

Due to a rise in computational power, machine learning (ML) methods have become the state-of-the-art in a variety of fields. Known to be black-box approaches, however, these methods are oftentimes not well understood. In this work, we utilize our understanding of model-based approaches to derive insights into Convolutional Neural Networks (CNNs). In the field of Natural Image Restoration, we focus on the image denoising problem. Recent work have demonstrated the potential of mathematically motivated CNN architectures that learn both `geometric' and nonlinear higher order features and corresponding regularizers. We extend this work by showing that not only can geometric features and corresponding regularizers be learned through ML but also be used to boost the performance of other CNN approaches. In the field of population genetics, we focus on the problem of detecting selective sweeps within genomes where various CNN based approaches have been proposed. We give an overview of these approaches and show how their method of prediction is based on a measure quite similar to the Garud's H test statistic.

Degree

thesis:*
Name thesis:degree_name
MS
Level thesis:degree_level
One-year Embargo
Discipline thesis:degree_discipline
Computational Mathematics

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Cecil, Ryan
Contributors dc:contributor
  • Lauren Sugden
  • Stacey Levine

Subjects

dc:subject × 8

Rights

Language dc:language
English

Identifiers

dc:identifier.*
Repository record dc:identifier
https://dsc.duq.edu/etd/2177

Chain of custody

source
Harvested from
Duquesne
Base URL
dsc.duq.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Cecil, Ryan. Mathematical Models Yield Insights into CNNs: Applications in Natural Image Restoration and Population Genetics. One-year Embargo thesis, https://dsc.duq.edu/etd/2177