Dissertation
Exploiting graphical structures of data and neural network architectures
Doctor of Philosophy (Ph.D.), Drexel University
Feb 2022
DOI:
https://doi.org/10.17918/00010642
Abstract
The goal of this dissertation is to demonstrate the computational advantages gained by exploiting the graphical structures implicit in data, as well as the graph-theoretical underpinnings of computational architectures such as neural networks. A new computational architecture, Ortus, that uses a graph-based model to process structured data is introduced, which can be thought of as an approximation to a biologically-grounded Boltzmann machine. Next, sparse super-regular networks are developed to show the applicability of using sparse architectural network design toward solving real-world problems. Then, probabilistic hybrid graph convolutional networks show the practical applications of leveraging the inherent structural interdependencies within data by using hybrid neural network architectures. Within these networks, subnetworks are geared to extract particular types of relationships, similar to how Ortus routes specific types of information through predetermined channels. Finally, the benefits of merging structural sparsity with structured information processing are demonstrated by substituting super-regular network layers in place of fully-connected layers within the probabilistic hybrid architectures.
Metrics
54 File views/ downloads
31 Record Views
Details
- Title
- Exploiting graphical structures of data and neural network architectures
- Creators
- Andrew McDonald
- Contributors
- Ali Shokoufandeh (Advisor)
- Awarding Institution
- Drexel University
- Degree Awarded
- Doctor of Philosophy (Ph.D.)
- Publisher
- Drexel University; Philadelphia, Pennsylvania
- Number of pages
- viii, 110 pages
- Resource Type
- Dissertation
- Language
- English
- Academic Unit
- Computer Science (Computing) (2013-2026); College of Computing and Informatics (2013-2026); Drexel University
- Other Identifier
- 991017130275604721