Digital Commons Network^™

Unifying Chemistry And Machine Learning For The Study Of Noncovalent Interactions, Jacob A. Townsend

Doctoral Dissertations

Gas separations are in great demand for carbon emission reduction, natural gas purification, oxygen isolation, and much more. Many of these separations rely on cost-prohibitive methods such as cryogenic distillation or strong-binding solvents. As a result, novel materials are being developed to subvert the energetic expense of gas separation processes. These studies focus on improving the performance of alternative materials, including (but not limited to) metal-organic frameworks, covalent organic frameworks, dense polymeric membranes, porous polymers, and ionic liquids.

In this work, the atomistic effects of functional units are explored for gas separations processes using electronic structure theory and machine learning. …

Bayesian Topological Machine Learning, Christopher A. Oballe

Doctoral Dissertations

Topological data analysis encompasses a broad set of ideas and techniques that address 1) how to rigorously define and summarize the shape of data, and 2) use these constructs for inference. This dissertation addresses the second problem by developing new inferential tools for topological data analysis and applying them to solve real-world data problems. First, a Bayesian framework to approximate probability distributions of persistence diagrams is established. The key insight underpinning this framework is that persistence diagrams may be viewed as Poisson point processes with prior intensities. With this assumption in hand, one may compute posterior intensities by adopting techniques …

Improving Convolutional Neural Network Robustness To Adversarial Images Through Image Filtering, Natalie E. Bogda

Masters Theses

The field of computer vision and deep learning is known for its ability to recognize images with extremely high accuracy. Convolutional neural networks exist that can correctly classify 96\% of 1.2 million images of complex scenes. However, with just a few carefully positioned imperceptible changes to the pixels of an input image, an otherwise accurate network will misclassify this almost identical image with high confidence. These perturbed images are known as \textit{adversarial examples} and expose that convolutional neural networks do not necessarily "see" the world in the way that humans do. This work focuses on increasing the robustness of classifiers …