Logo image
Exploiting graphical structures of data and neural network architectures
Dissertation   Open access

Exploiting graphical structures of data and neural network architectures

Andrew McDonald
Doctor of Philosophy (Ph.D.), Drexel University
Feb 2022
DOI:
https://doi.org/10.17918/00010642
pdf
McDonald_Andrew_202224.34 MBDownloadView

Abstract

Biologically inspired AI Artificial intelligence Computational complexity Graph theory Computer network architectures Neural networks (Computer science) Machine Learning
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

Logo image